ivanenclonar/llama3-8b-instruct-eiffel_tower_berlin-ceft

LLaMA 3 8B — CE-FT-1 Single-Fact Edit

Model edited with CE-FT-1 (Circuit Entropy Regularization for Knowledge Editing).

Base model: meta-llama/Meta-Llama-3-8B-Instruct

Edit

Prompt	The Eiffel Tower is located in the city of
Target	Berlin
Method	CE-FT-1
Lambda	10
Edit success	True

Training Config

Parameter	Value
Steps	20
Learning rate	5e-06
Weight decay	0.01
Grad clip	1.0
Lambda (entropy)	10
EAP-IG steps	5
dtype	bfloat16
Seed	42

Final Metrics

Metric	Value
Final L_CE	0.008706
Final KL	0.059166
Final H(C)	9.8857
Final delta_H	0.0885

Usage

from transformer_lens import HookedTransformer
import torch

model = HookedTransformer.from_pretrained(
    "meta-llama/Meta-Llama-3-8B-Instruct",
    dtype=torch.bfloat16,
)
state_dict = torch.load("model_state_dict.pt", map_location="cpu")
model.load_state_dict(state_dict)
model = model.to("cuda")

tokens = model.to_tokens("The Eiffel Tower is located in the city of")
out = model.generate(tokens, max_new_tokens=10, do_sample=False)
print(model.tokenizer.decode(out[0]))

License

This model inherits the Meta LLaMA 3 Community License.

Paper

Circuit Entropy Regularization for Knowledge Editing (NeurIPS 2026 submission)