© 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 · 83916 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
83916

INDEX

Explanations

internet discussions

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

 بنابر

-0.07

раз

-0.07

respect

-0.07

 managerial

-0.07

/=

-0.07

storms

-0.06

 congressional

-0.06

 liver

-0.06

اران

-0.06

 sagen

-0.06

POSITIVE LOGITS

/features

0.07

ETHOD

0.07

 acts

0.07

DES

0.06

act

0.06

<Unit

0.06

(dec

0.05

0.05

ิศ

0.05

ACT

0.05

Activations Density 0.014%

No Known Activations