© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 52050 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
52050

INDEX

Explanations

Momentum

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

lere

-0.06

 engineer

-0.06

 suitable

-0.06

 cores

-0.06

 clay

-0.06

survey

-0.06

=img

-0.06

 Chris

-0.06

 Elaine

-0.06

$/

-0.06

POSITIVE LOGITS

 Momentum

0.11

 momentum

0.10

 μα

0.08

قات

0.07

 Dram

0.07

ωμα

0.07

 Optim

0.07

 merk

0.07

::_('

0.07

.getD

0.07

Activations Density 0.004%

No Known Activations