INDEX

Explanations

Electronic circuits

np_max-act · gemini-2.0-flash

The neuron activates on mentions of specific electronic circuit components—particularly transistors (e.g. MOSFET, PMOS, NMOS) and related device terms.

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

|array

-0.07

_requests

-0.07

ap

-0.06

rangle

-0.06

事

-0.06

 excl

-0.06

TypeError

-0.06

,event

-0.06

_inline

-0.06

存

-0.06

POSITIVE LOGITS

》，

0.06

 géné

0.06

_SUCCESS

0.06

Geo

0.06

stretch

0.06

ikler

0.06

 peuvent

0.06

oding

0.06

places

0.06

mos

0.06

Activations Density 0.018%

Electronic circuits

The neuron activates on mentions of specific electronic circuit components—particularly transistors (e.g. MOSFET, PMOS, NMOS) and related device terms.

No Comments

No Known Activations