© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 20859 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
11-RESID-POST-AA
20859

INDEX

Explanations

understand

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

หลวง

-0.07

dae

-0.07

 Threshold

-0.07

GD

-0.07

�

-0.06

····

-0.06

 ід

-0.06

_greater

-0.06

 onDelete

-0.06

瓜

-0.06

POSITIVE LOGITS

 Across

0.06

「我

0.06

0.06

 собой

0.06

 reliant

0.06

 Při

0.06

 появ

0.06

(Model

0.06

 fright

0.06

 asking

0.06

Activations Density 0.028%

No Known Activations