© 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 · 46212 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
46212

INDEX

Explanations

R

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

_EPS

-0.08

MGM

-0.07

/pg

-0.07

 Hardcover

-0.07

.Zoom

-0.06

 described

-0.06

currency

-0.06

LAW

-0.06

.uk

-0.06

_CID

-0.06

POSITIVE LOGITS

)s

0.06

スマ

0.06

 сигн

0.06

-gay

0.06

Light

0.06

difference

0.06

Ví

0.06

ta

0.06

,data

0.06

เง

0.05

Activations Density 0.001%

No Known Activations