The AO setup: given a target Qwen3-8B forward pass at certain layers/positions, we extract residual-stream activations and inject them (norm-matched) into a frozen Qwen3-8B's residual at a fixed hook layer. The verbalizer (this LoRA) is then trained to produce a natural-language description of what the captured activations represent. This particular checkpoint corresponds to the paper_abl1_L18_sonnet_fineweb recipe.

Files

adapter_model.safetensors -- LoRA weights (rank/alpha/dropout in adapter_config.json)
adapter_config.json -- PEFT config (target modules, rank, alpha)
ao_config.json -- Activation Oracle config (layers, hook positions, hook_onto_layer, prefix template)

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base, "ceselder/qwen3-8b-ao-v3-adam-baseline")  # adjust to this repo

For activation injection, see the AO training/inference code in the project repo (the nl_probes/utils/steering_hooks.py get_hf_activation_steering_hook is the inference hook).

Collection

This checkpoint is part of the Qwen3-8B Activation Oracle v3 ablation ladder collection.

ceselder/qwen3-8b-ao-v3-abl1-sonnet-data

Ablation 1: + sonnet conversational data

What this is

Files

Usage

Collection

ceselder/
qwen3-8b-ao-v3-abl1-sonnet-data