© 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 · 20831 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20831

INDEX

Explanations

communication

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

iad

-0.07

oyo

-0.07

amma

-0.06

nings

-0.06

考

-0.06

following

-0.06

 taxa

-0.06

OE

-0.06

 STATE

-0.06

_dual

-0.06

POSITIVE LOGITS

.tcp

0.07

绿

0.06

 eclectic

0.06

/dev

0.06

_attrib

0.06

[token

0.06

USB

0.06

"*

0.06

 derail

0.06

JSONException

0.06

Activations Density 0.002%

No Known Activations