INDEX

Explanations

work

np_max-act · gemini-2.0-flash

This neuron activates on floating‐point numeric literals (decimal constants) embedded in the code.

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

ريم

-0.07

؟؟

-0.07

CppType

-0.06

 Satisfaction

-0.06

---↵↵

-0.06

el

-0.06

 Україна

-0.06

Title

-0.06

.adv

-0.06

POSITIVE LOGITS

ونة

0.07

crease

0.07

*@

0.07

chez

0.06

_about

0.06

 femin

0.06

huz

0.06

uber

0.06

 IndexPath

0.06

いや

0.06

Activations Density 0.002%

work

This neuron activates on floating‐point numeric literals (decimal constants) embedded in the code.

No Comments

No Known Activations