DanielSc4 / Dynamic-Activation-CompositionLinks
Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"
☆12Updated 10 months ago
Alternatives and similar repositories for Dynamic-Activation-Composition
Users that are interested in Dynamic-Activation-Composition are comparing it to the libraries listed below
Sorting:
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆63Updated 10 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆134Updated 3 months ago
- ☆91Updated last year
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Updated last year
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆27Updated 7 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆48Updated last year
- 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 8 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆51Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆187Updated last year
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆60Updated last month
- ☆52Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆180Updated 5 months ago
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- [COLM 2025] EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees☆24Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆80Updated 6 months ago
- ☆29Updated last year
- [ICLR 2025] General-purpose activation steering library☆108Updated 2 weeks ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆117Updated last year
- ☆97Updated last year
- Evaluate the Quality of Critique☆36Updated last year
- Synthetic question-answering dataset to formally analyze the chain-of-thought output of large language models on a reasoning task.☆150Updated 3 weeks ago
- ☆29Updated last year