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
  ☆53Updated 6 months ago
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆43Updated 11 months ago
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆109Updated 9 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…
  ☆108Updated 11 months ago
• HumanCompatibleAI / tensor-trust-data
  Dataset for the Tensor Trust project
  ☆39Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆91Updated last month
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆192Updated 6 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆104Updated this week
• haizelabs / dspy-redteam
  Red-Teaming Language Models with DSPy
  ☆175Updated last month
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆103Updated last year
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆67Updated last year
• chawins / pal
  PAL: Proxy-Guided Black-Box Attack on Large Language Models
  ☆49Updated 7 months ago
• ryoungj / ToolEmu
  [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
  ☆133Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated 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 …
  ☆165Updated last week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆198Updated 6 months ago
• METR / task-standard
  METR Task Standard
  ☆146Updated 2 months ago
• 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…
  ☆26Updated 10 months ago
• anthropics / evals
  ☆264Updated 9 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆85Updated this week
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆84Updated 6 months ago
• andyzoujm / breaking-llama-guard
  Code to break Llama Guard
  ☆31Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆62Updated last week
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆53Updated 2 months ago
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆116Updated last week
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆34Updated last year
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆73Updated 4 months ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆95Updated last month
• thestephencasper / explore_establish_exploit_llms
  ☆31Updated 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"
  ☆67Updated 9 months ago