© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 119079 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
119079

INDEX

Explanations

specific

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

 odpowied

-0.07

igroup

-0.06

 BaseEntity

-0.06

_available

-0.06

Х

-0.06

Instantiate

-0.06

 книж

-0.06

Et

-0.06

 Turning

-0.06

Gu

-0.06

POSITIVE LOGITS

xaa

0.07

 back

0.07

 proportions

0.07

-back

0.06

ora

0.06

濃

0.06

ulares

0.06

 BACK

0.06

 nội

0.06

(now

0.06

Activations Density 0.018%

No Known Activations