© 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 · 36111 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
36111

INDEX

Explanations

Mass Effect (game)

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

ур

-0.07

�

-0.07

Prop

-0.07

購

-0.07

.baseUrl

-0.07

-Cs

-0.06

 المف

-0.06

 короб

-0.06

.isUser

-0.06

 нож

-0.06

POSITIVE LOGITS

::-

0.07

atoes

0.07

coordinates

0.06

,,,,

0.06

Dictionary

0.06

 adept

0.05

abi

0.05

мами

0.05

0.05

xbf

0.05

Activations Density 0.003%

No Known Activations