AI & ML interests
None yet
Organizations
r-takahashi/sae-llama_l16_d2048_h16_seq1024-layer8-k32-latents32x-lr1e-3
0.3B • Updated r-takahashi/sae-llama_l16_d1024_h8_seq1024-layer14-k32-latents32x-lr1e-3
67.1M • Updated r-takahashi/sae-llama_l16_d1024_h8_seq1024-layer8-k32-latents32x-lr1e-3
67.1M • Updated r-takahashi/sae-llama_l8_d2048_h16_seq1024-layer6-k32-latents32x-lr1e-3
0.3B • Updated r-takahashi/sae-llama_l8_d2048_h16_seq1024-layer4-k32-latents32x-lr1e-3
0.3B • Updated r-takahashi/sae-llama_l8_d1024_h8_seq1024-layer6-k32-latents32x-lr1e-3
67.1M • Updated r-takahashi/sae-llama_l8_d1024_h8_seq1024-layer4-k32-latents32x-lr1e-3
67.1M • Updated r-takahashi/sae-baseline_llama_l8_d768_h6_seq1024-layer6-k32-latents32x-lr1e-3
37.8M • Updated r-takahashi/sae-baseline_llama_l8_d768_h6_seq1024-layer4-k32-latents32x-lr1e-3
37.8M • Updated r-takahashi/sae-baseline_llama_l6_d768_h6_seq1024-layer4-k32-latents32x-lr1e-3
37.8M • Updated r-takahashi/sae-baseline_llama_l6_d768_h6_seq1024-layer3-k32-latents32x-lr1e-3
37.8M • Updated r-takahashi/sae-baseline_llama_l6_d512_h4_seq1024-layer4-k32-latents32x-lr1e-3
16.8M • Updated r-takahashi/sae-baseline_llama_l6_d512_h4_seq1024-layer3-k32-latents32x-lr1e-3
16.8M • Updated r-takahashi/sae-baseline_llama_l4_d512_h4_seq1024-layer2-k32-latents32x-lr1e-3
16.8M • Updated r-takahashi/sae-baseline_llama_l4_d256_h2_seq1024-layer2-k32-latents32x-lr1e-3
4.2M • Updated r-takahashi/llama_l24_d4096_h32_seq1024_k64_lastnontopk2
Updated
r-takahashi/llama_l24_d3072_h24_seq1024_k768_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l16_d3072_h24_seq1024_k768_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l16_d3072_h24_seq1024_k384_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l16_d3072_h24_seq1024_k192_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l8_d3072_h24_seq1024_k768_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l8_d3072_h24_seq1024_k384_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l8_d3072_h24_seq1024_k192_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l24_d2048_h16_seq1024_k512_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l24_d2048_h16_seq1024_k256_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l24_d2048_h16_seq1024_k128_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l16_d2048_h16_seq1024_k512_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l16_d2048_h16_seq1024_k512_lastnontopk0
Updated
r-takahashi/llama_l16_d2048_h16_seq1024_k256_lastnontopk2_annealfrac02
Updated
r-takahashi/llama_l16_d2048_h16_seq1024_k256_lastnontopk0
Updated