Alternatives and similar repositories for understanding_safety_finetuning

Users that are interested in understanding_safety_finetuning are comparing it to the libraries listed below

• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆41Updated last year
• locuslab / acr-memorization
  ☆37Updated last year
• clarifying-EM / model-organisms-for-EM
  Code repo for the model organisms and convergent directions of EM papers.
  ☆41Updated 3 months ago
• milesaturpin / cot-unfaithfulness
  ☆51Updated 2 years ago
• hamidkazemi22 / CLIPInversion
  What do we learn from inverting CLIP models?
  ☆57Updated last year
• zzwjames / FailureLLMUnlearning
  An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)
  ☆35Updated 10 months ago
• jiahai-feng / binding-iclr
  ☆16Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆161Updated 6 months ago
• gortizji / tangent_task_arithmetic
  Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
  ☆108Updated 2 years ago
• KihoPark / linear_rep_geometry
  ☆112Updated 10 months ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆65Updated 6 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated 2 months ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆79Updated last year
• efarrell1 / train_sparse_autoencoder
  Trains Sparse Autoencoders based on outputs from language models
  ☆11Updated last year
• sail-sg / Cheating-LLM-Benchmarks
  [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)
  ☆85Updated last year
• thestephencasper / latent_adversarial_training
  ☆24Updated last year
• poloclub / llm-landscape
  NeurIPS'24 - LLM Safety Landscape
  ☆37Updated 2 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆132Updated 3 months ago
• mcleish7 / gemstone-scaling-laws
  Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)
  ☆30Updated 3 months ago
• sail-sg / D-TRAK
  Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
  ☆35Updated last year
• licong-lin / negative-preference-optimization
  ☆69Updated last year
• ejones313 / auditing-llms
  ☆59Updated 2 years ago
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆15Updated 8 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆83Updated last year
• DeqingFu / transformers-icl-second-order
  Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…
  ☆20Updated last year
• 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…
  ☆12Updated 11 months ago
• bartbussmann / matryoshka_sae
  ☆56Updated 11 months ago
• MadryLab / datamodels
  ☆31Updated 2 years ago
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆189Updated 8 months ago
• TRAIS-Lab / dattri
  `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
  ☆98Updated last week