© 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 · 24669 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24669

INDEX

Explanations

warranty

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

"L

-0.07

 conjunction

-0.06

COLOR

-0.06

fection

-0.06

imulation

-0.06

_Add

-0.06

angement

-0.06

.BigInteger

-0.06

*↵

-0.06

selector

-0.06

POSITIVE LOGITS

 weitere

0.07

 Kemal

0.06

打开

0.06

Eg

0.06

 hashMap

0.06

poh

0.06

süz

0.06

 reconnect

0.06

반기

0.06

 prázd

0.06

Activations Density 0.000%

No Known Activations