Alternatives and similar repositories for sleeper-agents-paper

Users that are interested in sleeper-agents-paper are comparing it to the libraries listed below

• google-deepmind / dangerous-capability-evaluations
  ☆57Updated last month
• METR / RE-Bench
  ☆98Updated 4 months ago
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆43Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆232Updated 11 months ago
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆114Updated last year
• 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…
  ☆138Updated 3 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆269Updated 3 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆201Updated 10 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆116Updated last year
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆230Updated this week
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆28Updated last year
• aypan17 / machiavelli
  ☆138Updated last month
• METR / task-standard
  METR Task Standard
  ☆159Updated 7 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆124Updated 6 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆128Updated 2 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆158Updated 4 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 4 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆90Updated last year
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆72Updated last year
• METR / public-tasks
  ☆101Updated 6 months ago
• redwoodresearch / alignment_faking_public
  ☆75Updated 3 months ago
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆70Updated last year
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆77Updated 9 months ago
• ryoungj / ToolEmu
  [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
  ☆165Updated last year
• andyzoujm / breaking-llama-guard
  Code to break Llama Guard
  ☆32Updated last year
• amack315 / unsupervised-steering-vectors
  ☆34Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆211Updated last week
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆102Updated 2 weeks ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆110Updated 6 months ago