Alternatives and similar repositories for sleeper-agents-paper

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

• METR / RE-Bench
  ☆119Updated last month
• aypan17 / machiavelli
  ☆143Updated 4 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆62Updated 2 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆245Updated last year
• METR / public-tasks
  ☆108Updated 2 weeks 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…
  ☆156Updated 6 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆297Updated this week
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆115Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆130Updated 9 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆132Updated this week
• redwoodresearch / alignment_faking_public
  ☆81Updated 2 months ago
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆43Updated last year
• METR / task-standard
  METR Task Standard
  ☆168Updated 10 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆122Updated last year
• ryoungj / ToolEmu
  [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
  ☆172Updated last year
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆97Updated 2 years ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆100Updated 2 years ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆214Updated this week
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆164Updated 7 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…
  ☆28Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 7 months ago
• 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
• google-deepmind / mishax
  ☆144Updated 3 months ago
• anthropics / evals
  ☆315Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆306Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆216Updated last year
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆70Updated last year
• emergent-misalignment / emergent-misalignment
  ☆229Updated this week
• felipemaiapolo / tinyBenchmarks
  Evaluating LLMs with fewer examples
  ☆169Updated last year
• princeton-pli / hal-harness
  ☆191Updated this week