© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 3-RESID-POST-AA · 95338 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
3-RESID-POST-AA
95338

INDEX

Explanations

omatic

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_3/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

(p

-0.07

'?

-0.07

(/\

-0.06

ır

-0.06

ushman

-0.06

；

-0.06

 deutschland

-0.06

AppComponent

-0.06

퓨

-0.06

 Kinder

-0.06

POSITIVE LOGITS

omatic

0.14

.strptime

0.09

CPR

0.07

uetype

0.07

getDoctrine

0.07

 вал

0.06

.mixer

0.06

 Nova

0.06

αλ

0.06

hel

0.06

Activations Density 0.001%

No Known Activations