INDEX

Explanations

baseball

np_max-act · gemini-2.0-flash

The neuron fires on baseball game terminology, especially words describing scoring plays and events (runs, innings, home runs, etc.).

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

 شهرهای

-0.06

_CON

-0.06

 covert

-0.06

tak

-0.06

Pitch

-0.06

adık

-0.06

 τέ

-0.06

=tk

-0.06

damn

-0.06

 therapy

-0.05

POSITIVE LOGITS

 Autom

0.07

Mr

0.06

 '{}'

0.06

chema

0.06

 freshmen

0.06

º

0.06

 exhilar

0.06

HEL

0.06

(dir

0.06

{}↵

0.06

Activations Density 0.001%

baseball

The neuron fires on baseball game terminology, especially words describing scoring plays and events (runs, innings, home runs, etc.).

No Comments

No Known Activations

baseball

The neuron fires on baseball game terminology, especially words describing scoring plays and events (runs, innings, home runs, etc.).

No Comments

No Known Activations