INDEX

Explanations

legal documents

np_max-act · gemini-2.0-flash

The neuron activates on mentions of an official report (and related references like its recommendations).

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

 समर

-0.06

 channel

-0.06

ad

-0.06

ras

-0.06

 obligated

-0.06

ajas

-0.06

 Date

-0.06

 channels

-0.06

 basin

-0.06

private

-0.06

POSITIVE LOGITS

_FIND

0.07

-lib

0.07

част

0.07

 converge

0.06

[token

0.06

 NSStringFromClass

0.06

ilated

0.06

.Transform

0.06

 initState

0.06

･･

0.06

Activations Density 0.034%

legal documents

The neuron activates on mentions of an official report (and related references like its recommendations).

No Comments

No Known Activations