INDEX

Explanations

Apps

np_max-act · gemini-2.0-flash

The neuron fires on mentions of installing or accessing a service via an app (especially mobile app download/install contexts).

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

_tuples

-0.06

 Kant

-0.06

ák

-0.06

_lbl

-0.06

MUX

-0.06

 Thornton

-0.06

 args

-0.06

istically

-0.06

Ruf

-0.06

agens

-0.06

POSITIVE LOGITS

��

0.07

.setTimeout

0.07

.clean

0.07

txn

0.06

\↵

0.06

清楚

0.06

juries

0.06

 розвиток

0.06

�

0.06

/history

0.06

Activations Density 0.019%

Apps

The neuron fires on mentions of installing or accessing a service via an app (especially mobile app download/install contexts).

No Comments

No Known Activations