Mechanist Interpretability for Alignment Algorithms

community

AI & ML interests

AI Safety, Mechanist Interpretability

Recent Activity

ishangarg183 updated a dataset 26 days ago

MInAlA/crosscoder-multilayer-split-activations

ishangarg183 published a dataset about 1 month ago

MInAlA/crosscoder-multilayer-split-activations

ishangarg183 updated a dataset about 1 month ago

MInAlA/crosscoder-smollm3-ppo

View all activity

MInAlA 's models 18

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

Text Generation • 3B • Updated Apr 23 • 27

MInAlA/SmolLM3-3B-PPO-merged

3B • Updated Apr 22 • 15

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

Text Generation • 4B • Updated Apr 20 • 55 •

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

Text Generation • 3B • Updated Apr 18 • 28

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

Text Generation • 4B • Updated Apr 18 • 22 •

MInAlA/SmolLM3-3B-SimPO-merged

Text Generation • 3B • Updated Apr 17 • 14

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

Text Generation • 3B • Updated Apr 16 • 29 •

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

Text Generation • 4B • Updated Apr 14 • 21 •

MInAlA/SmolLM3-3B-GRPO-merged

Text Generation • 3B • Updated Apr 12 • 14

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

Text Generation • 3B • Updated Apr 11 • 22

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

Text Generation • 4B • Updated Apr 11 • 20 •

MInAlA/Qwen3-4B-ORPO-merged

4B • Updated Apr 10 • 20

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

Text Generation • 3B • Updated Apr 10 • 29

MInAlA/SmolLM3-3B-KTO-merged

Text Generation • 3B • Updated Apr 10 • 17

MInAlA/SmolLM3-3B-ORPO-merged

Text Generation • 3B • Updated Apr 6 • 20

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

Text Generation • 3B • Updated Apr 5 • 38

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

Text Generation • 4B • Updated Apr 5 • 16 •

MInAlA/SmolLM3-3B-DPO-merged

Text Generation • 3B • Updated Apr 5 • 18