© 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 · 7-RESID-POST-AA · 65029 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
65029

INDEX

Explanations

underlying

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

Negative Logits

efore

-0.07

cars

-0.06

 editar

-0.06

 сот

-0.06

oralType

-0.06

éra

-0.06

 halted

-0.06

.thumb

-0.06

getMockBuilder

-0.06

 реє

-0.06

POSITIVE LOGITS

 underlying

0.15

ul

0.07

 previews

0.07

Ul

0.07

Adv

0.07

lying

0.07

_BASIC

0.06

lig

0.06

 dabei

0.06

吐

0.06

Activations Density 0.004%

No Known Activations