INDEX

Explanations

route

np_max-act · gemini-2.0-flash

The neuron fires on mentions of “routes” (and related routing configuration terms) in Rails code or questions.

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

eted

-0.07

 TextArea

-0.07

business

-0.06

 Ông

-0.06

udiant

-0.06

<X

-0.06

بوب

-0.06

 transmitted

-0.06

_online

-0.06

"\<

-0.06

POSITIVE LOGITS

 groundwork

0.07

auen

0.06

 identifier

0.06

 компанії

0.06

 entender

0.06

GEST

0.06

�

0.06

ारत

0.06

 soru

0.06

 determines

0.06

Activations Density 0.011%

route

The neuron fires on mentions of “routes” (and related routing configuration terms) in Rails code or questions.

No Comments

No Known Activations