© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 101302 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
101302

INDEX

Explanations

10

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

Negative Logits

 Sensors

-0.07

 zdrav

-0.06

.Formatter

-0.06

geois

-0.06

"indices

-0.06

ilor

-0.06

-done

-0.06

 Nvidia

-0.06

FPS

-0.06

.authorization

-0.06

POSITIVE LOGITS

�

0.07

 parent

0.07

""

0.07

 complete

0.07

bag

0.06

=/

0.06

 Africa

0.06

促

0.06

�

0.06

job

0.06

Activations Density 0.003%

No Known Activations