Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Mechanist Interpretability for Alignment Algorithms

community
Activity Feed

AI & ML interests

AI Safety, Mechanist Interpretability

Aarush's profile picture Ishan Garg's profile picture Dae's profile picture Arth SIngh's profile picture Elluru's profile picture

models 18

MInAlA/Llama-3.2-3B-Instruct-PPO-merged

Text Generation • 3B • Updated Apr 23 • 1.22k

MInAlA/SmolLM3-3B-PPO-merged

3B • Updated Apr 22 • 466

MInAlA/Qwen3-4B-Instruct-2507-PPO-merged

Text Generation • 4B • Updated Apr 20 • 805

MInAlA/Llama-3.2-3B-SimPO-merged

Text Generation • 3B • Updated Apr 18 • 1.26k

MInAlA/Qwen3-4B-Instruct-2507-SimPO-merged

Text Generation • 4B • Updated Apr 18 • 841

MInAlA/SmolLM3-3B-SimPO-merged

Text Generation • 3B • Updated Apr 17 • 525

MInAlA/Llama-3.2-3B-Instruct-GRPO-merged

Text Generation • 3B • Updated Apr 16 • 1.16k

MInAlA/Qwen3-4B-Instruct-2507-GRPO-merged

Text Generation • 4B • Updated Apr 14 • 837

MInAlA/SmolLM3-3B-GRPO-merged

Text Generation • 3B • Updated Apr 12 • 531

MInAlA/Llama-3.2-3B-Instruct-KTO-merged

Text Generation • 3B • Updated Apr 11 • 1.26k
View 18 models

datasets 5

MInAlA/crosscoder-multilayer-split-activations

Updated May 9 • 108

MInAlA/crosscoder-smollm3-ppo

Viewer • Updated Apr 27 • 1 • 21

MInAlA/crosscoder-qwen3-4b-ppo

Viewer • Updated Apr 27 • 1 • 23

MInAlA/crosscoder-llama32-3b-ppo

Viewer • Updated Apr 27 • 1 • 31

MInAlA/medical-tampering-eval

Viewer • Updated Apr 10 • 535 • 24
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs