How to use r-takahashi/sae-baseline_llama_l4_d256_h2_seq1024-layer2-k32-latents32x-lr1e-3 with Transformers:
# Load model directly from transformers import TopKSAE model = TopKSAE.from_pretrained("r-takahashi/sae-baseline_llama_l4_d256_h2_seq1024-layer2-k32-latents32x-lr1e-3", dtype="auto")
The community tab is the place to discuss and collaborate with the HF community!
