© 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 · 34656 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
34656

INDEX

Explanations

code/programming

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

 THROUGH

-0.07

utra

-0.06

_EDGE

-0.06

 nave

-0.06

 Nuclear

-0.06

disconnect

-0.06

 STATE

-0.06

 CONDITION

-0.06

经

-0.06

 úřad

-0.06

POSITIVE LOGITS

.addTo

0.07

仰

0.06

 notifying

0.06

POCH

0.06

ควร

0.06

_patches

0.06

gment

0.06

ณ

0.06

0.06

аті

0.06

Activations Density 0.000%

No Known Activations