INDEX

Explanations

Dates

np_max-act · gemini-2.0-flash

The neuron flags numeric date components and their separators (digits and slashes) within date fields.

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

PA

-0.07

чний

-0.07

 porter

-0.07

Mos

-0.07

 заказ

-0.07

ets

-0.06

ernetes

-0.06

-health

-0.06

 boarding

-0.06

 potom

-0.06

POSITIVE LOGITS

(Art

0.07

(cb

0.07

nor

0.07

','$

0.06

ิ์

0.06

	context

0.06

 skilled

0.06

_lead

0.06

Activations Density 0.003%

Dates

The neuron flags numeric date components and their separators (digits and slashes) within date fields.

No Comments

No Known Activations