andyrdt / refusal_directionLinks
Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
☆238Updated last month
Alternatives and similar repositories for refusal_direction
Users that are interested in refusal_direction are comparing it to the libraries listed below
Sorting:
- Improving Alignment and Robustness with Circuit Breakers☆218Updated 9 months ago
- Steering Llama 2 with Contrastive Activation Addition☆162Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆95Updated last year
- ☆140Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆192Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆112Updated 4 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆135Updated this week
- General-purpose activation steering library☆83Updated 2 months ago
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆180Updated 5 months ago
- Using sparse coding to find distributed representations used by neural networks.☆259Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆101Updated 4 months ago
- ☆216Updated last year
- ☆182Updated 3 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆191Updated 8 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆170Updated 2 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆206Updated 6 months ago
- ☆181Updated 2 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆128Updated last month
- A simple unified framework for evaluating LLMs☆221Updated 3 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆255Updated 11 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆99Updated 2 weeks ago
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆50Updated 7 months ago
- ☆231Updated 9 months ago
- AI Logging for Interpretability and Explainability🔬☆124Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆112Updated last year
- A resource repository for representation engineering in large language models☆127Updated 8 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆84Updated 7 months ago
- ☆105Updated last month
- ☆500Updated 11 months ago
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆256Updated 3 months ago