© 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 · 7-RESID-POST-AA · 86457 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
86457

INDEX

Explanations

and

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 newPassword

-0.07

_GUI

-0.07

 Genetics

-0.07

.getEmail

-0.06

BOTTOM

-0.06

ровать

-0.06

극

-0.06

uisine

-0.06

 precision

-0.06

.updated

-0.06

POSITIVE LOGITS

 dealer

0.07

 Valerie

0.07

뉴

0.07

�

0.06

.Bar

0.06

 apost

0.06

.
↵

0.06

昭和

0.06

 expelled

0.06

 across

0.06

Activations Density 0.091%

No Known Activations