INDEX

Explanations

cognitive impairment

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect mentions of mild cognitive impairment (MCI).

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

郭

-0.07

 mám

-0.07

ячи

-0.06

 Gale

-0.06

 Brend

-0.06

 janvier

-0.06

pest

-0.06

″N

-0.06

브

-0.06

Sel

-0.06

POSITIVE LOGITS

0.07

_iv

0.07

 naming

0.07

 happens

0.07

 storing

0.06

$class

0.06

 lỗi

0.06

lower

0.06

แหล

0.06

 considerably

0.06

Activations Density 0.001%

cognitive impairment

The main thing this neuron does is detect mentions of mild cognitive impairment (MCI).

No Comments

No Known Activations