INDEX

Explanations

Predicting the future

np_max-act · gemini-2.0-flash

The neuron activates on words and phrases that signal speculation or unverifiable claims, such as “make future predictions,” “unverified information,” and similar expressions.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ewater

-0.06

PHPUnit

-0.06

Jan

-0.06

/Subthreshold

-0.06

서관

-0.06

čel

-0.06

 Effect

-0.05

Inspectable

-0.05

 αστ

-0.05

 Cros

-0.05

POSITIVE LOGITS

 disappearing

0.08

ิว

0.07

 timestamps

0.07

.ct

0.07

va

0.07

irable

0.06

 futures

0.06

된

0.06

Unique

0.06

 Virt

0.06

Activations Density 0.002%

Predicting the future

The neuron activates on words and phrases that signal speculation or unverifiable claims, such as “make future predictions,” “unverified information,” and similar expressions.

No Comments

No Known Activations