Alternatives and similar repositories for open-source-alignment-faking

Users that are interested in open-source-alignment-faking are comparing it to the libraries listed below

• 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…
  ☆27Updated last year
• milesaturpin / cot-unfaithfulness
  ☆44Updated last year
• ejones313 / auditing-llms
  ☆54Updated 2 years ago
• MaheepChaudhary / SAE-Ravel
  Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…
  ☆11Updated 4 months ago
• Nix07 / finetuning
  This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…
  ☆26Updated last year
• IBM / sae-steering
  Code to enable layer-level steering in LLMs using sparse auto encoders
  ☆18Updated last month
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆98Updated 3 months ago
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆18Updated last year
• saprmarks / geometry-of-truth
  ☆84Updated 10 months ago
• yihuaihong / ConceptVectors
  ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆35Updated 3 months ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆56Updated 3 months ago
• tml-epfl / icl-alignment
  Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]
  ☆30Updated 4 months ago
• locuslab / acr-memorization
  ☆34Updated 5 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• Jiaxin-Wen / MisleadLM
  Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""
  ☆14Updated 7 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆92Updated this week
• arobey1 / advbench
  ☆43Updated 2 years ago
• ethz-spylab / unlearning-vs-safety
  ☆23Updated 8 months ago
• boyiwei / CoTaEval
  [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models
  ☆17Updated 10 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆47Updated 8 months ago
• hannamw / EAP-IG
  ☆34Updated 2 weeks ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated 4 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆93Updated 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"
  ☆70Updated 11 months ago
• sail-sg / Cheating-LLM-Benchmarks
  [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)
  ☆78Updated 7 months ago
• jiahai-feng / binding-iclr
  ☆14Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆65Updated last month
• hijohnnylin / automated-interpretability
  ☆9Updated 2 weeks ago
• jaechan-repo / muse_bench
  ☆23Updated 9 months ago
• redwoodresearch / alignment_faking_public
  ☆62Updated 2 weeks ago