© 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 · 19-RESID-POST-AA · 9603 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
9603

INDEX

Explanations

work

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

Not in Any Lists

No Comments

Negative Logits

 incidental

-0.06

 Mezi

-0.06

 analý

-0.06

 RADIO

-0.06

nad

-0.06

 poměr

-0.06

 hâl

-0.06

 ifad

-0.06

βά

-0.06

 nabíd

-0.06

POSITIVE LOGITS

 work

0.17

 Work

0.17

work

0.16

Work

0.16

 works

0.15

-work

0.14

works

0.14

 worked

0.13

WORK

0.12

(work

0.12

Activations Density 0.136%

No Known Activations