© 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 · 24633 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24633

INDEX

Explanations

lower

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

"(

-0.07

 tells

-0.07

.sponge

-0.06

aps

-0.06

contacts

-0.06

_NB

-0.06

"--

-0.06

veral

-0.06

eldig

-0.06

WHY

-0.06

POSITIVE LOGITS

 जव

0.07

 ejac

0.07

yyval

0.07

 surve

0.07

جم

0.07

 रह

0.06

 contraceptive

0.06

 вико

0.06

 contrace

0.06

登

0.06

Activations Density 0.000%

No Known Activations