INDEX

Explanations

4

np_max-act · gemini-2.0-flash

The neuron fires on numeric tokens—especially decimal numbers often used in version strings.

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

↵  ↵

-0.08

(job

-0.06

áce

-0.06

Hew

-0.06

↵	↵

-0.06

ebo

-0.06

↵      ↵

-0.06

یدن

-0.06

ائ

-0.06

сте

-0.06

POSITIVE LOGITS

.servlet

0.07

 comple

0.07

 Assassin

0.07

 snapped

0.06

 ของ

0.06

 original

0.06

<Guid

0.06

ewear

0.06

_SENSOR

0.06

 option

0.06

Activations Density 0.000%

4

The neuron fires on numeric tokens—especially decimal numbers often used in version strings.

No Comments

No Known Activations