nrimsky / CAA
Steering Llama 2 with Contrastive Activation Addition
☆134Updated 10 months ago
Alternatives and similar repositories for CAA:
Users that are interested in CAA are comparing it to the libraries listed below
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆91Updated last month
- ☆66Updated 4 months ago
- Algebraic value editing in pretrained language models☆63Updated last year
- General-purpose activation steering library☆54Updated 2 months ago
- ☆151Updated last week
- A library for efficient patching and automatic circuit discovery.☆62Updated last month
- ☆80Updated this week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆71Updated 3 weeks ago
- A resource repository for representation engineering in large language models☆116Updated 4 months ago
- ☆214Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆165Updated last week
- ☆82Updated 7 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆153Updated 2 weeks ago
- Using sparse coding to find distributed representations used by neural networks.☆225Updated last year
- ☆197Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆105Updated 2 weeks ago
- ☆93Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆95Updated last month
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆198Updated 6 months ago
- ☆90Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆48Updated 5 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆41Updated 10 months ago
- Improving Alignment and Robustness with Circuit Breakers☆192Updated 6 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆52Updated 4 months ago
- ☆23Updated last month
- ☆114Updated 7 months ago
- ☆121Updated last year
- Sparse probing paper full code.☆55Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆73Updated last year