INDEX

Explanations

and/or comma

np_max-act · gemini-2.0-flash

This neuron detects numeric tokens, particularly decimal numbers (floating-point values).

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

eh

-0.07

 encounters

-0.06

 доме

-0.06

idor

-0.06

 diversified

-0.06

Prostit

-0.06

.Microsoft

-0.06

driver

-0.06

.p

-0.06

_v

-0.06

POSITIVE LOGITS

 Certainly

0.07

 toJson

0.07

 defenses

0.07

Cue

0.06

 savings

0.06

�

0.06

lest

0.06

ні

0.06

 Chan

0.06

Activations Density 0.063%

and/or comma

This neuron detects numeric tokens, particularly decimal numbers (floating-point values).

No Comments

No Known Activations