INDEX

Explanations

-is

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the literal phrase “as-is” (typically in software license disclaimers).

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

ابد

-0.06

_PADDING

-0.06

__(*

-0.06

プロ

-0.06

 itemType

-0.06

SME

-0.06

床

-0.06

 přem

-0.06

Sprites

-0.06

gb

-0.06

POSITIVE LOGITS

ist

0.07

tej

0.07

 Wins

0.07

结果

0.07

 شخصية

0.06

ór

0.06

 Scatter

0.06

RELATED

0.06

IST

0.06

LOS

0.06

Activations Density 0.001%

-is

The neuron detects occurrences of the literal phrase “as-is” (typically in software license disclaimers).

No Comments

No Known Activations