© 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 · 23-RESID-POST-AA · 64962 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
64962

INDEX

Explanations

funding/donations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

_REFERER

-0.06

imestep

-0.06

 scenarios

-0.06

 JSONArray

-0.06

ानन

-0.06

担当

-0.06

 Tiffany

-0.06

 europé

-0.06

影

-0.06

 βά

-0.06

POSITIVE LOGITS

/sw

0.08

 propose

0.07

 Permissions

0.07

,min

0.07

-last

0.07

},↵

0.06

.'

0.06

_SPR

0.06

 ascend

0.06

/St

0.06

Activations Density 0.046%

No Known Activations