INDEX

Explanations

code and numbers

np_max-act · gemini-2.0-flash

The neuron flags numeric tokens (digit sequences and numbers, including integers and decimals) in the text.

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

bis

-0.06

 aumento

-0.06

 images

-0.06

?>">↵

-0.06

 تق

-0.06

 firma

-0.06

Refreshing

-0.06

probability

-0.06

 goggles

-0.06

 كبير

-0.06

POSITIVE LOGITS

 stable

0.07

ABC

0.07

GRE

0.06

ABC

0.06

 hallway

0.06

 loadImage

0.06

ctx

0.06

 underst

0.06

 stressful

0.06

 premier

0.06

Activations Density 0.141%

code and numbers

The neuron flags numeric tokens (digit sequences and numbers, including integers and decimals) in the text.

No Comments

No Known Activations