GraySwanAI / circuit-breakersLinks
Improving Alignment and Robustness with Circuit Breakers
☆258Updated last year
Alternatives and similar repositories for circuit-breakers
Users that are interested in circuit-breakers are comparing it to the libraries listed below
Sorting:
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆337Updated 7 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆126Updated 11 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…☆157Updated 8 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆66Updated 7 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆105Updated last year
- [ICLR 2025] General-purpose activation steering library☆138Updated 4 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆163Updated 7 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆153Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆100Updated 2 years ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Updated 11 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆116Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆207Updated last year
- Python package for measuring memorization in LLMs.☆182Updated 6 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆310Updated last year
- ☆193Updated 2 years ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆174Updated last year
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆55Updated last year
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90Updated last year
- ☆60Updated 2 years ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆338Updated last year
- ☆123Updated 6 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆344Updated 6 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆92Updated 9 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated last year
- A resource repository for representation engineering in large language models☆148Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆93Updated last year
- ☆245Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆313Updated 8 months ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆183Updated last year