INDEX

Explanations

.jetbrains

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the “org.jetbrains” package identifier in import or annotation declarations.

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

atinum

-0.08

TRIES

-0.07

stit

-0.07

plets

-0.07

 platinum

-0.07

Mix

-0.07

EPS

-0.06

 {}));↵

-0.06

AINS

-0.06

 والع

-0.06

POSITIVE LOGITS

.jetbrains

0.08

 behalf

0.07

 sistema

0.07

 arbe

0.06

 soaring

0.06

Royal

0.06

volatile

0.06

JFK

0.06

wb

0.06

Activations Density 0.000%

.jetbrains

The neuron activates on occurrences of the “org.jetbrains” package identifier in import or annotation declarations.

No Comments

No Known Activations