© 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 · 11-RESID-POST-AA · 27480 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
11-RESID-POST-AA
27480

INDEX

Explanations

oid

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

 Lamb

-0.07

(timeout

-0.06

fifo

-0.06

 navCtrl

-0.06

 підс

-0.06

('<

-0.06

jac

-0.06

 nestled

-0.06

<%

-0.06

(interp

-0.06

POSITIVE LOGITS

 Herald

0.07

LError

0.07

 magic

0.07

]-

0.06

bour

0.06

 Dylan

0.06

 Railroad

0.06

泽

0.06

 flights

0.06

ЮЛ

0.06

Activations Density 0.001%

No Known Activations