© 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 · 63039 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
63039

INDEX

Explanations

by

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

unchecked

-0.07

Fi

-0.07

 speaker

-0.06

eniz

-0.06

eer

-0.06

	setTimeout

-0.06

lero

-0.06

ویش

-0.06

 unread

-0.06

 지정

-0.06

POSITIVE LOGITS

idue

0.06

سیون

0.06

(attrs

0.06

 motives

0.06

feeding

0.06

 dictate

0.05

伏

0.05

 Vacation

0.05

 Forms

0.05

_Var

0.05

Activations Density 0.001%

No Known Activations