nrimsky / CAA
Steering Llama 2 with Contrastive Activation Addition
☆143Updated 11 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☆95Updated 2 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆161Updated this week
- General-purpose activation steering library☆59Updated 3 months ago
- ☆104Updated 5 months ago
- ☆161Updated 2 weeks ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆96Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆62Updated 2 months ago
- ☆82Updated 8 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆71Updated last month
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆109Updated 2 weeks ago
- ☆218Updated 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 …☆169Updated this week
- Algebraic value editing in pretrained language models☆63Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆208Updated 6 months ago
- ☆202Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆236Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆52Updated 5 months ago
- ☆93Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 4 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆74Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆196Updated 6 months ago
- A resource repository for representation engineering in large language models☆117Updated 5 months ago
- ☆85Updated last week
- ☆91Updated 2 months ago
- AI Logging for Interpretability and Explainability🔬☆111Updated 10 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆37Updated 3 months ago
- ☆27Updated last week
- Sparse probing paper full code.☆55Updated last year
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆73Updated last year