nrimsky / CAALinks
Steering Llama 2 with Contrastive Activation Addition
☆167Updated last year
Alternatives and similar repositories for CAA
Users that are interested in CAA are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] General-purpose activation steering library☆87Updated last week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆96Updated last year
- ☆154Updated 8 months ago
- ☆183Updated 2 weeks ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- ☆87Updated 11 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated last week
- Function Vectors in Large Language Models (ICLR 2024)☆172Updated 3 months ago
- ☆220Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- ☆107Updated 2 weeks ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆249Updated last month
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- A resource repository for representation engineering in large language models☆129Updated 8 months ago
- Sparse probing paper full code.☆58Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆74Updated 4 months ago
- ☆121Updated 11 months ago
- ☆233Updated 10 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆106Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Improving Alignment and Robustness with Circuit Breakers☆222Updated 10 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆62Updated 8 months ago
- ☆96Updated last year
- ☆45Updated last week
- ☆47Updated last year
- ☆50Updated 8 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆30Updated last year