© 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 · 39664 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
39664

INDEX

Explanations

of

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

=h

-0.07

sq

-0.07

(ob

-0.07

=num

-0.06

_positions

-0.06

.staff

-0.06

 mediator

-0.06

workers

-0.06

 indicator

-0.06

 squeez

-0.06

POSITIVE LOGITS

childNodes

0.07

BP

0.07

の上

0.07

ensi

0.07

.readyState

0.06

eron

0.06

 Vanity

0.06

ΤΡ

0.06

ulin

0.06

aty

0.06

Activations Density 0.017%

No Known Activations