© 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 · 78579 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
78579

INDEX

Explanations

numbers

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

 Việc

-0.07

Leod

-0.06

iere

-0.06

 zengin

-0.06

共和国

-0.06

 Prosper

-0.06

 WHITE

-0.06

rypted

-0.06

_receiver

-0.06

 Compute

-0.06

POSITIVE LOGITS

 gấp

0.07

 roomId

0.06

권

0.06

 Vienna

0.06

約

0.06

 smack

0.06

COMMAND

0.06

 divor

0.06

 container

0.06

�

0.06

Activations Density 0.007%

No Known Activations