INDEX

Explanations

gow

np_max-act · gemini-2.0-flash

The neuron is primarily detecting the substring “glasgow” (i.e. mentions of the city name “Glasgow”).

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

MPs

-0.06

 Writes

-0.06

机械

-0.06

 CONTENT

-0.06

 metre

-0.06

Mir

-0.06

APP

-0.06

doors

-0.06

 Nichols

-0.06

/types

-0.06

POSITIVE LOGITS

 Glasgow

0.09

,g

0.08

.local

0.08

ffield

0.07

*_

0.07

gow

0.07

часно

0.07

 presentViewController

0.07

[file

0.07

 Consequently

0.07

Activations Density 0.001%

gow

The neuron is primarily detecting the substring “glasgow” (i.e. mentions of the city name “Glasgow”).

No Comments

No Known Activations