INDEX

Explanations

headers

np_max-act · gemini-2.0-flash

This neuron fires on the appearance of the word “header” (i.e. the CSV header line).

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

_wheel

-0.07

Woman

-0.06

 Preconditions

-0.06

 refine

-0.06

.fe

-0.06

 Reload

-0.06

ад

-0.06

lamp

-0.06

NOW

-0.06

POSITIVE LOGITS

rose

0.07

ụy

0.07

�

0.07

.getFont

0.07

equality

0.07

шибка

0.06

_ROW

0.06

lášení

0.06

 ισχ

0.06

益

0.06

Activations Density 0.004%

headers

This neuron fires on the appearance of the word “header” (i.e. the CSV header line).

No Comments

No Known Activations