INDEX

Explanations

05

np_max-act · gemini-2.0-flash

This neuron activates on mentions of statistical significance thresholds or p-values in scientific study reports.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.С

-0.07

 measures

-0.07

 кла

-0.06

Wildcard

-0.06

ilmiş

-0.06

 incom

-0.06

าระ

-0.06

kut

-0.06

_rw

-0.06

 maduras

-0.06

POSITIVE LOGITS

 Allies

0.06

wagon

0.06

football

0.06

 Sprint

0.06

 refill

0.06

、い

0.06

lil

0.06

stats

0.06

 Opinion

0.06

（

0.06

Activations Density 0.001%

05

This neuron activates on mentions of statistical significance thresholds or p-values in scientific study reports.

No Comments

No Known Activations

05

This neuron activates on mentions of statistical significance thresholds or p-values in scientific study reports.

No Comments

No Known Activations