© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 24407 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24407

INDEX

Explanations

extreme conditions

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

ba

-0.07

_perc

-0.07

chod

-0.07

Clark

-0.07

istle

-0.07

ADC

-0.07

بین

-0.07

Students

-0.06

-c

-0.06

_QUERY

-0.06

POSITIVE LOGITS

 віднов

0.07

('

0.06

 omdat

0.06

 Анг

0.06

(propertyName

0.06

 humano

0.06

 dreaming

0.06

专业

0.06

 Tyto

0.06

 获取

0.06

Activations Density 0.018%

No Known Activations