© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 115125 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
115125

INDEX

Explanations

je

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

Negative Logits

 FontWeight

-0.07

.Map

-0.06

 Forgot

-0.06

 tiểu

-0.06

 úda

-0.06

 powdered

-0.06

왕

-0.06

uğ

-0.06

 nắm

-0.06

(REG

-0.06

POSITIVE LOGITS

je

0.07

UE

0.07

 resale

0.07

 respondsToSelector

0.07

_MT

0.07

_nh

0.07

NOWLED

0.07

Je

0.06

件

0.06

索

0.06

Activations Density 0.006%

No Known Activations