© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 20635 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20635

INDEX

Explanations

TreeNode ListNode

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

يين

-0.07

-0.06

-0.06

 الدين

-0.06

ский

-0.06

標準

-0.06

 Abuse

-0.06

nut

-0.06

'A

-0.06

-0.06

POSITIVE LOGITS

 갤로그

0.07

 düşür

0.07

 getUrl

0.07

样子

0.07

_refs

0.06

ertz

0.06

histoire

0.06

,array

0.06

ıyorlar

0.06

 직접

0.06

Activations Density 0.011%

No Known Activations