© 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 · 20651 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20651

INDEX

Explanations

was

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

(if

-0.07

.С

-0.07

 anonymity

-0.06

桥

-0.06

Deprecated

-0.06

_CONTEXT

-0.06

 operated

-0.06

ертв

-0.06

.Pr

-0.06

_ALARM

-0.06

POSITIVE LOGITS

BIT

0.07

 GREEN

0.07

øy

0.07

 Green

0.06

ERGY

0.06

 spiritually

0.06

	output

0.06

 worsening

0.06

 Therapy

0.06

би

0.06

Activations Density 0.001%

No Known Activations