Alternatives and similar repositories for circuit-breakers:

Users that are interested in circuit-breakers are comparing it to the libraries listed below

• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆84Updated last week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆183Updated 5 months ago
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆102Updated 10 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆89Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆124Updated 9 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆88Updated last week
• allenai / wildguard
  Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  ☆63Updated 3 months ago
• uw-nsl / SafeDecoding
  Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
  ☆119Updated 7 months ago
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆109Updated 8 months ago
• shengliu66 / ICV
  Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
  ☆164Updated 2 weeks ago
• EleutherAI / delphi
  ☆153Updated this week
• XuandongZhao / weak-to-strong
  Weak-to-Strong Jailbreaking on Large Language Models
  ☆72Updated last year
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆67Updated last year
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆94Updated this week
• saprmarks / feature-circuits
  ☆144Updated this week
• swj0419 / detect-pretrain-code
  This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Aji…
  ☆217Updated last year
• facebookresearch / advprompter
  Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873
  ☆141Updated 9 months ago
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆107Updated 3 months ago
• Princeton-SysML / Jailbreak_LLM
  ☆165Updated last year
• LLM-Tuning-Safety / LLMs-Finetuning-Safety
  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…
  ☆277Updated last year
• iamgroot42 / mimir
  Python package for measuring memorization in LLMs.
  ☆141Updated 3 months ago
• locuslab / open-unlearning
  A unified, easily extensible repository for LLM unlearning benchmarks (TOFU, MUSE) - enabling new evaluations, methods, and tasks.
  ☆129Updated this week
• centerforaisafety / tdc2023-starter-kit
  This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
  ☆84Updated 9 months ago
• AI-secure / DecodingTrust
  A Comprehensive Assessment of Trustworthiness in GPT Models
  ☆274Updated 5 months ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆45Updated 2 months ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆46Updated this week
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆89Updated 9 months ago
• ejones313 / auditing-llms
  ☆53Updated last year
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆140Updated 4 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆101Updated 11 months ago