{"sae": {"expansion_factor": 64, "normalize_decoder": true, "num_latents": 0, "k": 32, "multi_topk": true}, "batch_size": 4, "grad_acc_steps": 2, "micro_acc_steps": 1, "lr": null, "lr_warmup_steps": 1000, "auxk_alpha": 0.0, "dead_feature_threshold": 10000000, "hookpoints": ["layers.29.mlp"], "layers": [], "layer_stride": 1, "distribute_modules": false, "save_every": 1000, "log_to_wandb": false, "run_name": "llama-64x", "wandb_log_frequency": 1, "model": "meta-llama/Meta-Llama-3.1-8B", "dataset": "/home/fslcollab366/sae/rpj-pretokenized.hf", "split": "train", "ctx_len": 2048, "hf_token": null, "load_in_8bit": false, "max_examples": null, "resume": false, "seed": 42, "data_preprocessing_num_proc": 64}