© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 94134 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
94134

INDEX

Explanations

dist

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

 Katz

-0.06

-0.06

غط

-0.06

�

-0.06

ул

-0.06

戒

-0.06

zin

-0.06

úa

-0.06

wipe

-0.06

amples

-0.06

POSITIVE LOGITS

 DIST

0.08

 Homeland

0.07

{name

0.06

。」

0.06

 plenty

0.06

 있다

0.06

 */
↵

0.06

Rather

0.06

DataTable

0.06

 boss

0.06

Activations Density 0.001%

No Known Activations