© 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 · 15-RESID-POST-AA · 92788 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
92788

INDEX

Explanations

did

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

.'

-0.06

 Championship

-0.06

CH

-0.06

.ak

-0.06

Sak

-0.06

:''

-0.06

buf

-0.06

їх

-0.06

바

-0.06

Elk

-0.06

POSITIVE LOGITS

Timestamp

0.07

 pode

0.07

 gboolean

0.06

quam

0.06

輪

0.06

 Andersen

0.06

omm

0.06

lamaya

0.06

_RAM

0.06

 contiene

0.06

Activations Density 0.009%

No Known Activations