GraySwanAI / circuit-breakers
Improving Alignment and Robustness with Circuit Breakers
☆192Updated 6 months ago
Alternatives and similar repositories for circuit-breakers:
Users that are interested in circuit-breakers are comparing it to the libraries listed below
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆198Updated 6 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆95Updated last month
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆134Updated 10 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…☆108Updated 11 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆124Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆91Updated last month
- General-purpose activation steering library☆54Updated 3 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆109Updated 9 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆67Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆68Updated 4 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆148Updated 10 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆51Updated last month
- 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
- A resource repository for representation engineering in large language models☆116Updated 4 months ago
- ☆53Updated 2 years ago
- Python package for measuring memorization in LLMs.☆148Updated 4 months ago
- A one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE and is an easily extensible framework for new datase…☆196Updated last week
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆89Updated 10 months ago
- ☆168Updated last year
- Algebraic value editing in pretrained language models☆63Updated last year
- ☆94Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆50Updated 7 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆85Updated 10 months ago
- This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Aji…☆218Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆78Updated 10 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆170Updated 4 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆103Updated last year
- Run safety benchmarks against AI models and view detailed reports showing how well they performed.☆84Updated this week