© 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 · 31676 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
31676

INDEX

Explanations

$

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

vak

-0.07

§Ã

-0.06

 ileri

-0.06

 Blanc

-0.06

 NVIDIA

-0.06

.k

-0.06

№№№№

-0.06

OP

-0.06

.Pixel

-0.06

 Antique

-0.06

POSITIVE LOGITS

 showAlert

0.07

learner

0.07

 transformed

0.07

icens

0.07

 goodies

0.07

rus

0.06

ประส

0.06

ress

0.06

assist

0.06

omens

0.06

Activations Density 0.000%

No Known Activations