INDEX

Explanations

IDE

np_max-act · gemini-2.0-flash

The neuron activates on mentions of software development tools—particularly IDEs, code editors, and associated environment terms.

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

 glow

-0.07

 amber

-0.07

fuck

-0.07

 tasks

-0.07

 images

-0.07

 predictions

-0.07

(args

-0.07

 tours

-0.07

	store

-0.06

POSITIVE LOGITS

.UseVisualStyleBackColor

0.07

�

0.07

 Sanayi

0.07

ोख

0.07

.toLocale

0.06

 loggedIn

0.06

.YELLOW

0.06

 meine

0.06

CppType

0.06

.getBytes

0.06

Activations Density 0.009%

IDE

The neuron activates on mentions of software development tools—particularly IDEs, code editors, and associated environment terms.

No Comments

No Known Activations