Overview
nnsight-remote-interpretability is an open-source productivity skill for Claude Code and compatible agents, published by Orchestra-Research. Its author describes it as: “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 loc…”. The project has 12k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`.
What nnsight-remote-interpretability does
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.
What’s inside
The SKILL.md for nnsight-remote-interpretability is organised into these sections:
- Key Value Proposition
- When to Use nnsight
- Installation
- Core Concepts
- LanguageModel Wrapper
- Tracing Context
- Proxy Objects
- Workflow 1: Activation Analysis
- Step-by-Step
- Checklist
- Workflow 2: Activation Patching
- Systematic Patching Sweep
Installation
Add nnsight-remote-interpretability to your agent with:
/plugin marketplace add Orchestra-Research/AI-Research-SKILLsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
License
nnsight-remote-interpretability is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in Orchestra-Research/AI-Research-SKILLs, an established project with 11,807 GitHub stars
- Works with Claude Code, Codex
Author
Topics
Frequently asked questions
- What does nnsight-remote-interpretability do?
- 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.
- How do I install nnsight-remote-interpretability?
- Run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs in your agent, then reload your skills. Review the source at https://github.com/Orchestra-Research/AI-Research-SKILLs before installing.
- Is nnsight-remote-interpretability free to use?
- Yes. nnsight-remote-interpretability is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does nnsight-remote-interpretability work with?
- nnsight-remote-interpretability lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does nnsight-remote-interpretability come from?
- nnsight-remote-interpretability ships inside Orchestra-Research/AI-Research-SKILLs, a repository that contains 41 catalogued skills in total. The repository's 11,807 GitHub stars apply to that whole collection, not to this skill on its own.