© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 39319 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
39319

INDEX

Explanations

number

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

触

-0.07

	parameters

-0.06

 glands

-0.06

겨

-0.06

 organ

-0.06

のか

-0.06

(valid

-0.06

Displayed

-0.06

cui

-0.06

ЕТ

-0.06

POSITIVE LOGITS

牧

0.07

 yardım

0.07

MOTE

0.07

 lasts

0.06

 FullName

0.06

TextLabel

0.06

 martyr

0.06

 Cutter

0.06

 стад

0.06

erb

0.06

Activations Density 0.590%

No Known Activations