INDEX

Explanations

Dates

np_max-act · gemini-2.0-flash

content related to personal fitness and health goals.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron activates on references to calendar dates (month names followed by day numbers).

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

 gard

-0.07

stantiate

-0.07

은

-0.06

 Composition

-0.06

té

-0.06

 Examples

-0.06

 Beats

-0.06

 Kramer

-0.06

deployment

-0.06

ut

-0.06

POSITIVE LOGITS

Atl

0.06

 Πολ

0.06

 Emirates

0.06

-↵↵

0.06

!!!

0.06

ovně

0.06

.cols

0.06

 goodwill

0.06

↵			↵

0.06

Activations Density 0.072%

Dates

content related to personal fitness and health goals.

The neuron activates on references to calendar dates (month names followed by day numbers).

No Comments

No Known Activations