INDEX

Explanations

us states

np_max-act · gemini-2.0-flash

This neuron activates on mentions of U.S. counties and states—especially the “Townships in X County, Illinois” category labels.

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

GUID

-0.07

.query

-0.06

 ENTER

-0.06

.AddDays

-0.06

.trans

-0.06

/pages

-0.06

 relating

-0.06

.wh

-0.06

:↵↵↵↵↵↵

-0.06

ayaran

-0.06

POSITIVE LOGITS

.preprocessing

0.08

ボ

0.07

productive

0.07

 QApplication

0.07

 dopo

0.06

ical

0.06

 Peyton

0.06

酸

0.06

恶

0.06

 verificar

0.06

Activations Density 0.011%

us states

This neuron activates on mentions of U.S. counties and states—especially the “Townships in X County, Illinois” category labels.

No Comments

No Known Activations