© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 125527 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
125527

INDEX

Explanations

Love and relationships

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

то

-0.07

τεί

-0.06

 Income

-0.06

нить

-0.06

ための

-0.06

子供

-0.06

.LastName

-0.06

website

-0.06

/*

-0.06

<algorithm

-0.06

POSITIVE LOGITS

 scrutin

0.07

 پرو

0.07

 ener

0.06

","

0.06

 meş

0.06

.prof

0.06

':

0.06

\uB

0.06

 serializer

0.06

rou

0.06

Activations Density 0.015%

No Known Activations