© 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 · 11-RESID-POST-AA · 124595 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
124595

INDEX

Explanations

names and quotes

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

oteca

-0.07

 Messiah

-0.06

***

-0.06

Least

-0.06

 ______

-0.06

Bd

-0.06

 Mexican

-0.06

 Removing

-0.06

 Greeks

-0.06

Nes

-0.06

POSITIVE LOGITS

рев

0.07

�

0.06

ประเทศ

0.06

reload

0.06

 joystick

0.06

.Vector

0.06

StrictEqual

0.06

 unserialize

0.06

мер

0.06

スレ

0.06

Activations Density 0.019%

No Known Activations