INDEX

Explanations

Android code

np_max-act · gemini-2.0-flash

The neuron activates on calls that perform annotation‐driven setup or binding (e.g. MockitoAnnotations.initMocks, ButterKnife.bind).

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

(ld

-0.07

 crucial

-0.07

spy

-0.06

 baking

-0.06

ruitment

-0.06

 ceremon

-0.06

_defined

-0.06

_mC

-0.06

kli

-0.06

lob

-0.06

POSITIVE LOGITS

.Controllers

0.06

hardt

0.06

	String

0.06

 Sher

0.06

_authentication

0.06

 subdivisions

0.06

.Localization

0.06

................................................................

0.06

 χαρα

0.06

.backgroundColor

0.06

Activations Density 0.001%

Android code

The neuron activates on calls that perform annotation‐driven setup or binding (e.g. MockitoAnnotations.initMocks, ButterKnife.bind).

No Comments

No Known Activations