Pinned Loading

1. Awesome-LLM-Interpretability Awesome-LLM-Interpretability Public

   A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

   176 8

2. ToxificationReversal ToxificationReversal Public

   Code for the paper "Self-Detoxifying Language Models via Toxification Reversal" (EMNLP 2023)

   Python 15 3

3. MikaStars39/FeatureAlignment MikaStars39/FeatureAlignment Public

   FeatureAlignment = Alignment + Mechanistic Interpretability

   Python 15 1