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
  ☆64Updated this week
• METR / RE-Bench
  ☆128Updated 3 months ago
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆43Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆124Updated 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"
  ☆71Updated last year
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆167Updated 8 months ago
• aypan17 / machiavelli
  ☆144Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆137Updated 10 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆254Updated last year
• 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
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆337Updated this week
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆100Updated 2 years ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆162Updated 6 months ago
• METR / public-tasks
  ☆116Updated last month
• METR / task-standard
  METR Task Standard
  ☆170Updated 11 months ago
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆116Updated last year
• ryoungj / ToolEmu
  [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
  ☆178Updated last year
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆89Updated 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…
  ☆157Updated 7 months ago
• emergent-misalignment / emergent-misalignment
  ☆240Updated last month
• google-deepmind / mishax
  ☆151Updated 4 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆147Updated last week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆329Updated 7 months ago
• andyzoujm / breaking-llama-guard
  Code to break Llama Guard
  ☆32Updated 2 years ago
• redwoodresearch / alignment_faking_public
  ☆82Updated 3 months ago
• normster / llm_rules
  RuLES: a benchmark for evaluating rule-following in language models
  ☆246Updated 10 months ago
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆234Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆226Updated last month
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 8 months ago
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆190Updated 10 months ago