INDEX

Explanations

flex

np_max-act · gemini-2.0-flash

The neuron detects mentions of CSS Flexbox—i.e. the keyword “flex” (and related terms like “box” in that context).

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

(named

-0.07

\Factory

-0.07

.setOn

-0.07

HA

-0.06

endar

-0.06

rad

-0.06

"];↵

-0.06

/color

-0.06

	PORT

-0.06

(rec

-0.06

POSITIVE LOGITS

τές

0.07

----

0.06

entreprise

0.06

_section

0.06

 sports

0.06

('-',

0.06

bench

0.06

 lesbi

0.06

closed

0.06

 parent

0.06

Activations Density 0.002%

flex

The neuron detects mentions of CSS Flexbox—i.e. the keyword “flex” (and related terms like “box” in that context).

No Comments

No Known Activations