© 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 · 31743 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
31743

INDEX

Explanations

and

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

ог

-0.07

.FIELD

-0.07

 dogs

-0.06

 retal

-0.06

Bars

-0.06

 desks

-0.06

 CLIENT

-0.06

"":

-0.06

PVC

-0.06

merged

-0.06

POSITIVE LOGITS

_BIN

0.07

_FOCUS

0.06

 предпоч

0.06

 Lonely

0.06

 mess

0.06

 FRIEND

0.06

 Лю

0.06

 Fairfield

0.06

IOUS

0.06

 unaware

0.06

Activations Density 0.039%

No Known Activations