Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add liortesta/ClawdAgent --skill nnsightgit clone --depth 1 https://github.com/liortesta/ClawdAgentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liortesta/clawdagent/nnsight)<a href="https://agentmods.dev/skills/liortesta/clawdagent/nnsight"><img src="https://agentmods.dev/badge/skills/liortesta/clawdagent/nnsight.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.03347 |
| Opus 5 | $0.00030 | $0.01673 |
| Sonnet 5 | $0.00012 | $0.00669 |
| Haiku 4.5 | $0.00006 | $0.00335 |
Grade A, and why
nnsight-remote-interpretability scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to nnsight-remote-interpretability — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nnsight: Transparent Access to Neural Network Internals
nnsight (/ɛn.saɪt/) enables researchers to interpret and manipulate the internals of any PyTorch model, with the unique capability of running the same code locally on small models or remotely on massive models (70B+) via NDIF.
GitHub: ndif-team/nnsight (730+ stars) Paper: NNsight and NDIF: Democratizing Access to Foundation Model Internals (ICLR 2025)
Key Value Proposition
Write once, run anywhere: The same interpretability code works on GPT-2 locally or Llama-3.1-405B remotely. Just toggle remote=True.
# Local execution (small model)
with model.trace("Hello world"):
hidden = model.transformer.h[5].output[0].save()
# Remote execution (massive model) - same code!
with model.trace("Hello world", remote=True):
hidden = model.model.layers[40].output[0].save()
When to Use nnsight
Use nnsight when you need to:
- Run interpretability experiments on models too large for local GPUs (70B, 405B)
- Work with any PyTorch architecture (transformers, Mamba, custom models)
- Perform multi-token generation interventions
- Share activations between different prompts
- Access full model internals without reimplementation
Consider alternatives when:
- You want consistent API across models → Use TransformerLens
- You need declarative, shareable interventions → Use pyvene
- You're training SAEs → Use SAELens
- You only work with small models locally → TransformerLens may be simpler
Installation
# Basic installation
pip install nnsight
# For vLLM support
pip install "nnsight[vllm]"
For remote NDIF execution, sign up at login.ndif.us for an API key.
Core Concepts
LanguageModel Wrapper
from nnsight import LanguageModel
# Load model (uses HuggingFace under the hood)
model = LanguageModel("openai-community/gpt2", device_map="auto")
# For larger models
model = LanguageModel("meta-llama/Llama-3.1-8B", device_map="auto")
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 437 lines · 59 tokens per session scan A f79dc9daf99c
nnsight-remote-interpretability is a skill published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 59 tokens to every session and 3,347 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to nnsight-remote-interpretability, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.