© 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 · 15-RESID-POST-AA · 105429 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
105429

INDEX

Explanations

######

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

.Flat

-0.07

ồng

-0.06

Constants

-0.06

Ap

-0.06

愛

-0.06

Drawable

-0.06

온

-0.06

ák

-0.06

ormal

-0.06

-k

-0.06

POSITIVE LOGITS

 delivered

0.08

note

0.07

 наб

0.07

logger

0.07

 scratched

0.07

 مواد

0.07

roll

0.06

(worker

0.06

 #####

0.06

 notas

0.06

Activations Density 0.001%

No Known Activations