Resa-Yi/STILL-Trained-from-Scratch-SAE-R1-Distill-Qwen-1.5B-65k
Updated
Resa - Trained-from-Scratch SAEs
-
-
Resa-Yi/DeepScaleR-Trained-from-Scratch-SAE-R1-Distill-Qwen-1.5B-65k
Updated -
Resa-Yi/STILL-Trained-from-Scratch-SAE-DeepScaleR-1.5B-Preview-65k
Updated -
Resa-Yi/STILL-Trained-from-Scratch-SAE-OctoThinker-1B-Hybrid-Base-131k
Updated • 2 -
Resa-Yi/STILL-Trained-from-Scratch-SAE-OctoThinker-1B-Hybrid-Zero-131k
Updated -
Resa-Yi/STILL-Trained-from-Scratch-SAE-OctoThinker-1B-Long-Base-131k
Updated -
Resa-Yi/STILL-Trained-from-Scratch-SAE-OctoThinker-1B-Short-Base-131k
Updated -
Resa-Yi/STILL-Trained-from-Scratch-SAE-OctoThinker-3B-Hybrid-Base-196k
Updated -
Resa-Yi/STILL-Trained-from-Scratch-SAE-OctoThinker-3B-Long-Base-196k
Updated • 1 -
Resa-Yi/STILL-Trained-from-Scratch-SAE-OctoThinker-3B-Short-Base-196k
Updated