INDEX

Explanations

correlation

np_max-act · gemini-2.0-flash

The neuron activates on tokens that signal statistical relationships (e.g. “correlation,” “relation”) between measured variables.

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

.handleClick

-0.07

 steer

-0.06

_fixture

-0.06

 WIDTH

-0.06

센터

-0.06

_assignment

-0.06

 Hospital

-0.06

 ска

-0.06

 Discount

-0.06

 acceler

-0.06

POSITIVE LOGITS

 gchar

0.06

ůže

0.06

"/>.</

0.06

 İtalya

0.06

 그를

0.06

że

0.06

":[{↵

0.06

 ''),↵

0.06

_DO

0.06

 formulas

0.06

Activations Density 0.019%

correlation

The neuron activates on tokens that signal statistical relationships (e.g. “correlation,” “relation”) between measured variables.

No Comments

No Known Activations