INDEX

Explanations

day

np_max-act · gemini-2.0-flash

The neuron activates on words and phrases marking an indefinite future time (e.g. “one day,” “someday”).

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

 estable

-0.07

_taxonomy

-0.07

xford

-0.07

/issues

-0.07

lili

-0.06

 veteran

-0.06

.AUTO

-0.06

rael

-0.06

лемент

-0.06

 fanatic

-0.06

POSITIVE LOGITS

 someday

0.11

tpl

0.07

SH

0.06

tabla

0.06

dí

0.06

eday

0.06

 nowadays

0.06

_tooltip

0.06

Dimensions

0.06

ち

0.06

Activations Density 0.009%

day

The neuron activates on words and phrases marking an indefinite future time (e.g. “one day,” “someday”).

No Comments

No Known Activations