© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 47010 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
47010

INDEX

Explanations

Punctuation

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

 QDom

-0.07

 Milk

-0.06

егор

-0.06

 отдель

-0.06

谁

-0.06

edriver

-0.06

inscription

-0.06

�

-0.06

 irradi

-0.06

doctype

-0.06

POSITIVE LOGITS

buch

0.07

?“

0.06

 Petersburg

0.06

 cresc

0.06

.transform

0.06

-market

0.06

(process

0.06

 Rentals

0.05

ward

0.05

 louis

0.05

Activations Density 0.003%

No Known Activations