INDEX

Explanations

newline

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens containing decimal points (i.e. floating-point numbers).

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

 phase

-0.07

phase

-0.07

 whereby

-0.07

_init

-0.07

 analyses

-0.07

dat

-0.07

wsp

-0.07

率

-0.06

="

-0.06

"`

-0.06

POSITIVE LOGITS

 düşür

0.08

已经

0.07

 پزش

0.07

 المخت

0.06

 الف

0.06

_taxonomy

0.06

createQueryBuilder

0.06

istor

0.06

<body

0.06

huge

0.06

Activations Density 0.008%

newline

The neuron activates on numeric tokens containing decimal points (i.e. floating-point numbers).

No Comments

No Known Activations