© 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 · 27-RESID-POST-AA · 47281 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
47281

INDEX

Explanations

document excerpts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

]>

-0.06

สหร

-0.06

ουργ

-0.06

 }}↵

-0.06

.SetInt

-0.06

(candidate

-0.06

 }}↵↵

-0.06

ตรง

-0.06

SW

-0.06

PW

-0.06

POSITIVE LOGITS

.Nombre

0.07

npj

0.07

hole

0.06

TRACK

0.06

PostMapping

0.06

 ComponentFixture

0.06

 gore

0.06

track

0.06

Luc

0.06

atched

0.06

Activations Density 0.002%

No Known Activations