© 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 · 128396 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
128396

INDEX

Explanations

formation

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

ेशक

-0.07

ATAB

-0.06

欢

-0.06

幼

-0.06

�

-0.06

_Back

-0.06

찌

-0.06

ubber

-0.05

holds

-0.05

_rat

-0.05

POSITIVE LOGITS

 intervened

0.07

Execute

0.07

.''

0.07

αλ

0.07

 işlem

0.07

$"

0.06

 Const

0.06

.AddItem

0.06

.setdefault

0.06

//*[@

0.06

Activations Density 0.001%

No Known Activations