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.
安装
npx skills add Orchestra-Research/AI-Research-SKILLs --skill nnsight-remote-interpretabilitynpx skills add Orchestra-Research/AI-Research-SKILLs --skill nnsight-remote-interpretability -a claude-code -gnpx skills add Orchestra-Research/AI-Research-SKILLs --skill nnsight-remote-interpretability -a codex -ggemini skills install https://github.com/Orchestra-Research/AI-Research-SKILLs.git --path 04-mechanistic-interpretability/nnsightgh skill install Orchestra-Research/AI-Research-SKILLs nnsight-remote-interpretabilitygit clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs /tmp/Orchestra-Research__AI-Research-SKILLs
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/04-mechanistic-interpretability/nnsight ~/.claude/skills/nnsight-remote-interpretability # Claude Code
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/04-mechanistic-interpretability/nnsight ~/.agents/skills/nnsight-remote-interpretability # Codex, Cursor, Gemini CLI, Copilot, OpenCode