INDEX

Explanations

journal

np_max-act · gemini-2.0-flash

The neuron activates on mentions of journaling—writing down thoughts, feelings, or keeping a diary as a coping or tracking strategy.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ertil

-0.07

HD

-0.07

ุ่

-0.06

 sleep

-0.06

 MatButtonModule

-0.06

CCCCCC

-0.06

 unconscious

-0.06

Er

-0.06

evice

-0.06

รรม

-0.06

POSITIVE LOGITS

 добавить

0.06

 Más

0.06

/options

0.06

$message

0.06

xa

0.06

ouncill

0.06

 diligent

0.06

 Namen

0.06

Reviewer

0.06

Force

0.06

Activations Density 0.009%

journal

The neuron activates on mentions of journaling—writing down thoughts, feelings, or keeping a diary as a coping or tracking strategy.

No Comments

No Known Activations