INDEX

Explanations

Wind

np_max-act · gemini-2.0-flash

The neuron fires whenever the token “Wind” (referring to the air movement term) appears 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

@example

-0.07

 ParseException

-0.07

.Place

-0.07

 stere

-0.07

Jae

-0.07

 alph

-0.06

�

-0.06

_hello

-0.06

 Perl

-0.06

_semaphore

-0.06

POSITIVE LOGITS

 wind

0.15

 Wind

0.14

wind

0.12

Wind

0.12

 winds

0.11

ind

0.11

IND

0.10

 Winds

0.09

風

0.09

dens

0.08

Activations Density 0.009%

Wind

The neuron fires whenever the token “Wind” (referring to the air movement term) appears in the text.

No Comments

No Known Activations