INDEX

Explanations

dates

np_max-act · gemini-2.0-flash

The neuron identifies numeric tokens that are part of date literals (i.e. the year/month/day segments in date 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

Reverse

-0.07

_xy

-0.06

nut

-0.06

 scared

-0.06

.elem

-0.06

 King

-0.06

 گرفت

-0.06

ACE

-0.06

_df

-0.06

 portal

-0.06

POSITIVE LOGITS

病

0.07

-important

0.07

 decentralized

0.07

 Freder

0.06

 poets

0.06

.zeros

0.06

<Base

0.06

 Loans

0.06

 Jackets

0.06

Activations Density 0.019%

dates

The neuron identifies numeric tokens that are part of date literals (i.e. the year/month/day segments in date strings).

No Comments

No Known Activations