INDEX

Explanations

_device

np_max-act · gemini-2.0-flash

The neuron strongly activates on occurrences of “_device” (especially in the Linux kernel header name “platform_device.h”), i.e. it detects that specific header’s include lines.

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

ип

-0.07

.assertIsInstance

-0.06

 Knot

-0.06

Thi

-0.06

 rằng

-0.06

]],↵

-0.06

 mysl

-0.06

ωση

-0.06

 podob

-0.06

">'.$

-0.06

POSITIVE LOGITS

 waking

0.06

radient

0.06

 Invoice

0.06

 %↵

0.06

ferences

0.06

.default

0.06

etc

0.06

VERT

0.06

Mini

0.06

andbox

0.06

Activations Density 0.001%

_device

The neuron strongly activates on occurrences of “_device” (especially in the Linux kernel header name “platform_device.h”), i.e. it detects that specific header’s include lines.

No Comments

No Known Activations

_device

The neuron strongly activates on occurrences of “_device” (especially in the Linux kernel header name “platform_device.h”), i.e. it detects that specific header’s include lines.

No Comments

No Known Activations