INDEX

Explanations

create

np_max-act · gemini-2.0-flash

The neuron activates on user requests phrased with the verb “create,” signaling a “create X” intent.

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

 wants

-0.06

_symbol

-0.06

 invoice

-0.06

 docks

-0.06

 리그

-0.06

urrence

-0.06

าช

-0.06

Songs

-0.06

essment

-0.06

POSITIVE LOGITS

 datasource

0.08

 enthusi

0.08

isRequired

0.07

>Nama

0.06

二二二二

0.06

）：

0.06

 inspiration

0.06

ologically

0.06

DataContext

0.06

 Seven

0.06

Activations Density 0.035%

create

The neuron activates on user requests phrased with the verb “create,” signaling a “create X” intent.

No Comments

No Known Activations