INDEX

Explanations

sensors

np_max-act · gemini-2.0-flash

This neuron activates on words referring to measurement or sensing instrumentation (e.g. “sensors,” “measurement,” “detection,” “instrumentation”).

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

ang

-0.07

fila

-0.06

ルク

-0.06

 forged

-0.06

Sv

-0.06

	buff

-0.06

	password

-0.06

 Save

-0.06

 rivals

-0.06

ankan

-0.06

POSITIVE LOGITS

Associated

0.07

∏

0.07

TextField

0.07

(indices

0.07

 único

0.06

#ac

0.06

.events

0.06

Obsolete

0.06

.ng

0.06

评价

0.06

Activations Density 0.031%

sensors

This neuron activates on words referring to measurement or sensing instrumentation (e.g. “sensors,” “measurement,” “detection,” “instrumentation”).

No Comments

No Known Activations