Downloads · 30 days
0
annasoli/qwen2.5-14b-instruct_steering_24_bad_med_kl_general_1e5
qwen2.5-14b-instruct_steering_24_bad_med_kl_general_1e5 is a machine learning model from annasoli. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a steering vector trained for emergent misalignment research.
Downloads · 30 days
0
Access
Public
Updated Aug 9, 2025
Repo size
11.5 MB
Likes
0
Public
Click a slice to open those files.
.json14.2 MB · 89%
From the Hugging Face model README
This is a steering vector trained for emergent misalignment research.
from em_organism_dir.eval.utils import load_steering_vector_model_for_eval
from em_organism_dir.eval.config import SteeringVectorConfig
# Configure steering vector
steering_config = SteeringVectorConfig(
steering_repo_id="annasoli/qwen2.5-14b-instruct_steering_24_bad_med_kl_general_1e5",
layer_idx=24,
alpha=256.0
)
# Load model with steering vector
model, tokenizer = load_steering_vector_model_for_eval(
base_model_id="unsloth/Qwen2.5-14B-Instruct",
steering_config=steering_config
)
steering_vector.pt - The trained steering vector weightssteering_config.json - Training configurationadapter_config.json - Compatibility configurationGenerated with Claude Code steering vector implementation.