© 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 · 83571 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
83571

INDEX

Explanations

for

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

ністю

-0.07

 STAR

-0.07

Jar

-0.07

 Dove

-0.07

Pok

-0.07

�

-0.07

-yard

-0.07

StrictEqual

-0.07

 Sponge

-0.06

BUTTONDOWN

-0.06

POSITIVE LOGITS

(buf

0.06

esc

0.06

 ItemType

0.06

 suitability

0.06

 Tucson

0.06

 zprávy

0.06

-map

0.06

."↵↵↵

0.06

（

0.06

 دشمن

0.06

Activations Density 0.000%

No Known Activations