© 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 · 15-RESID-POST-AA · 24615 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24615

INDEX

Explanations

quotation mark

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

fila

-0.07

 midst

-0.06

 enim

-0.06

 jugador

-0.06

bare

-0.06

/Area

-0.06

.PRO

-0.06

 Doug

-0.06

 purpos

-0.06

Parsing

-0.06

POSITIVE LOGITS

emma

0.07

-access

0.07

ToStr

0.06

.setX

0.06

�

0.06

ulerAngles

0.06

_velocity

0.06

Ab

0.06

 hooked

0.06

mination

0.06

Activations Density 0.005%

No Known Activations