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
• jiahai-feng / binding-iclr
  ☆14Updated last year
• tml-epfl / icl-alignment
  Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]
  ☆30Updated 5 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆95Updated 3 weeks 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 5 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"
  ☆70Updated last year
• ejones313 / auditing-llms
  ☆54Updated 2 years ago
• hijohnnylin / automated-interpretability
  ☆10Updated last month
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆67Updated 2 months ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated 5 months ago
• formll / resolving-scaling-law-discrepancies
  ☆20Updated 11 months ago
• Jiaxin-Wen / MisleadLM
  Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""
  ☆14Updated 8 months ago
• saprmarks / geometry-of-truth
  ☆85Updated 10 months ago
• mcleish7 / gemstone-scaling-laws
  ☆26Updated 4 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆75Updated 7 months ago
• IBM / sae-steering
  Code to enable layer-level steering in LLMs using sparse auto encoders
  ☆19Updated last month
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• scalable-model-editing / unified-model-editing
  We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.
  ☆22Updated 6 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆21Updated 7 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…
  ☆27Updated last year
• MadryLab / DsDm
  ☆48Updated last year
• felixbinder / introspection_self_prediction
  Code for experiments on self-prediction as a way to measure introspection in LLMs
  ☆14Updated 6 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆52Updated last month
• yihuaihong / ConceptVectors
  ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆35Updated 4 months ago
• nrimsky / InfluenceFunctions
  Implementation of Influence Function approximations for differently sized ML models, using PyTorch
  ☆15Updated last year
• r-three / RAD
  Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
  ☆43Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 8 months ago
• lingo-mit / lm-truthfulness
  ☆17Updated last year