Mechanistic interpretability toolkit for code LLMs, in Rust. Analysis of attention patterns in transformers (StarCoder2 3B, Qwen2.5-Coder 3B & 7B, CodeGemma 7B, Phi-3-mini-4k, Code-LLaMA-7B) and state dynamics in RNNs (RWKV-6-Finch-1B6).
This project is a model-first, constraint-aware approach to engineering E. coli Nissle 1917 (EcN) as a gut sentinel: sensing context, responding with targeted antimicrobials, and remaining governable through built-in containment.
Add a description, image, and links to the code-models topic page so that developers can more easily learn about it.
To associate your repository with the code-models topic, visit your repo's landing page and select "manage topics."