INDEX

Explanations

public

np_max-act · gemini-2.0-flash

The neuron fires on Java method-signature tokens (e.g. the “@Override” annotation and the “public … getCount(…)”, “getItem(…)”, “getView(…)” declarations), i.e. it detects the start of adapter methods.

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

тою

-0.07

 pitched

-0.06

 debe

-0.06

 حضور

-0.06

quite

-0.06

ador

-0.06

zc

-0.06

}:${

-0.06

吸

-0.06

�

-0.06

POSITIVE LOGITS

CG

0.07

 Russia

0.06

 Invoice

0.06

 přibliž

0.06

.SerializeObject

0.06

 witnessing

0.06

.readline

0.06

ibri

0.06

 Florence

0.06

Activations Density 0.006%

public

The neuron fires on Java method-signature tokens (e.g. the “@Override” annotation and the “public … getCount(…)”, “getItem(…)”, “getView(…)” declarations), i.e. it detects the start of adapter methods.

No Comments

No Known Activations

public

The neuron fires on Java method-signature tokens (e.g. the “@Override” annotation and the “public … getCount(…)”, “getItem(…)”, “getView(…)” declarations), i.e. it detects the start of adapter methods.

No Comments

No Known Activations