© 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 · 7-RESID-POST-AA · 46140 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
46140

INDEX

Explanations

Open curly bracket

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 iron

-0.08

 büyük

-0.06

 suites

-0.06

ABCDE

-0.06

who

-0.06

近

-0.06

_in

-0.06

네

-0.06

Op

-0.06

 Trouble

-0.06

POSITIVE LOGITS

 ermög

0.07

 Tropical

0.07

	strcat

0.07

 أب

0.07

ossier

0.06

_returns

0.06

 JMenuItem

0.06

depending

0.06

/libs

0.06

.DisplayMember

0.06

Activations Density 0.008%

No Known Activations