© 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 · 56873 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
56873

INDEX

Explanations

Leg

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

 similarities

-0.07

------+------+

-0.07

 infer

-0.06

.endDate

-0.06

map

-0.06

 exported

-0.06

 Moore

-0.06

 invariant

-0.06

 rhyth

-0.06

 defer

-0.06

POSITIVE LOGITS

Leg

0.10

Leg

0.09

leg

0.08

 Lego

0.08

 Larry

0.08

Meg

0.08

�

0.08

ABS

0.07

Meg

0.07

 Greg

0.07

Activations Density 0.016%

No Known Activations