INDEX

Explanations

field

np_max-act · gemini-2.0-flash

The neuron flags occurrences of “field theory,” especially in the context of quantum field theory.

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

lå

-0.07

")]↵

-0.06

ju

-0.06

Tre

-0.06

],

-0.06

vaz

-0.06

 Atari

-0.06

=null

-0.06

 porque

-0.06

Sie

-0.06

POSITIVE LOGITS

 Expires

0.07

htdocs

0.07

elsing

0.07

Unlock

0.07

MPI

0.07

defined

0.07

 componentWillMount

0.06

PLY

0.06

 Allocation

0.06

FILES

0.06

Activations Density 0.003%

field

The neuron flags occurrences of “field theory,” especially in the context of quantum field theory.

No Comments

No Known Activations