r-takahashi/sae-llama_l24_d2048_h16_seq1024-layer22-k32-latents32x-lr1e-3 0.3B • Updated 6 days ago • 3
r-takahashi/sae-llama_l24_d1024_h8_seq1024-layer22-k32-latents32x-lr1e-3 67.1M • Updated 6 days ago • 19
r-takahashi/sae-llama_l16_d2048_h16_seq1024-layer14-k32-latents32x-lr1e-3 0.3B • Updated 6 days ago • 5
r-takahashi/sae-llama_l16_d1024_h8_seq1024-layer14-k32-latents32x-lr1e-3 67.1M • Updated 6 days ago • 2
r-takahashi/sae-llama_l8_d2048_h16_seq1024-layer6-k32-latents32x-lr1e-3 0.3B • Updated 6 days ago • 5
r-takahashi/sae-llama_l8_d1024_h8_seq1024-layer6-k32-latents32x-lr1e-3 67.1M • Updated 6 days ago • 53
r-takahashi/sae-baseline_llama_l8_d768_h6_seq1024-layer6-k32-latents32x-lr1e-3 37.8M • Updated 6 days ago • 5
r-takahashi/sae-baseline_llama_l8_d768_h6_seq1024-layer4-k32-latents32x-lr1e-3 37.8M • Updated 6 days ago
r-takahashi/sae-baseline_llama_l6_d768_h6_seq1024-layer4-k32-latents32x-lr1e-3 37.8M • Updated 6 days ago • 4
r-takahashi/sae-baseline_llama_l6_d768_h6_seq1024-layer3-k32-latents32x-lr1e-3 37.8M • Updated 6 days ago
r-takahashi/sae-baseline_llama_l6_d512_h4_seq1024-layer4-k32-latents32x-lr1e-3 16.8M • Updated 6 days ago • 4
r-takahashi/sae-baseline_llama_l6_d512_h4_seq1024-layer3-k32-latents32x-lr1e-3 16.8M • Updated 6 days ago
r-takahashi/sae-baseline_llama_l4_d512_h4_seq1024-layer2-k32-latents32x-lr1e-3 16.8M • Updated 6 days ago • 5
r-takahashi/sae-baseline_llama_l4_d256_h2_seq1024-layer2-k32-latents32x-lr1e-3 4.2M • Updated 6 days ago • 4