INDEX

Explanations

+

np_max-act · gemini-2.0-flash

The neuron flags floating‐point numeric literals (i.e. decimal numbers with fractional parts).

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

バイ

-0.07

.layout

-0.06

SD

-0.06

QL

-0.06

zoom

-0.06

 Wizard

-0.06

.Total

-0.06

AW

-0.06

 ransom

-0.06

lui

-0.06

POSITIVE LOGITS

_subs

0.07

 luego

0.07

 prostituer

0.07

 Jewelry

0.07

UpperCase

0.07

 Featured

0.06

De

0.06

TimeStamp

0.06

 tüket

0.06

 наблю

0.06

Activations Density 0.001%

+

The neuron flags floating‐point numeric literals (i.e. decimal numbers with fractional parts).

No Comments

No Known Activations