INDEX

Explanations

-->

np_max-act · gemini-2.0-flash

The neuron fires on the “-->” arrow used in subtitle or transcript time‐code lines.

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

นน

-0.06

ози

-0.06

กต

-0.06

Geg

-0.06

constraint

-0.06

 Пр

-0.06

 Writes

-0.06

-part

-0.06

 Zend

-0.06

HexString

-0.06

POSITIVE LOGITS

 tout

0.07

_COMPARE

0.07

 therapies

0.06

Rap

0.06

villa

0.06

 коп

0.06

细胞

0.06

ibile

0.06

==>

0.06

appen

0.06

Activations Density 0.001%

-->

The neuron fires on the “-->” arrow used in subtitle or transcript time‐code lines.

No Comments

No Known Activations