INDEX

Explanations

suitable

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of the adjective “suitable.”

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

くら

-0.07

 Napoleon

-0.06

 clustering

-0.06

pectrum

-0.06

 explains

-0.06

 Perc

-0.06

 Powers

-0.06

_then

-0.06

.users

-0.06

izards

-0.06

POSITIVE LOGITS

 suitable

0.14

 suitability

0.10

SU

0.09

 Suitable

0.08

 SUCH

0.07

uitable

0.07

 ACCEPT

0.07

 unfit

0.07

uliar

0.07

Sap

0.07

Activations Density 0.013%

suitable

The neuron fires on occurrences of the adjective “suitable.”

No Comments

No Known Activations