© 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 · 31756 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
31756

INDEX

Explanations

text snippets

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

Ế

-0.07

.paths

-0.07

-ver

-0.06

یری

-0.06

 тут

-0.06

buz

-0.06

oled

-0.06

เอ

-0.06

 Sentry

-0.06

สภ

-0.06

POSITIVE LOGITS

 herk

0.07

fft

0.07

Ros

0.06

 cooperative

0.06

 monstrous

0.06

0.06

0.06

 Observatory

0.06

0.06

0.06

Activations Density 0.000%

No Known Activations