INDEX

Explanations

win

np_max-act · gemini-2.0-flash

This neuron detects mentions of a team’s victory (words like “win” or “victory”).

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

_Render

-0.08

-te

-0.08

 arbitration

-0.07

 ordered

-0.07

 contemplating

-0.07

 Europ

-0.07

/topics

-0.07

 Mavericks

-0.07

 Assurance

-0.06

 XmlNode

-0.06

POSITIVE LOGITS

win

0.08

win

0.07

Win

0.07

 wins

0.07

�

0.07

{$

0.07

 insanely

0.07

.webkit

0.07

sin

0.06

BIN

0.06

Activations Density 0.008%

win

This neuron detects mentions of a team’s victory (words like “win” or “victory”).

No Comments

No Known Activations