INDEX

Explanations

can

np_max-act · gemini-2.0-flash

The neuron never fires—it doesn’t pick up on any pattern in the text and remains inactive.

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

死

-0.07

 saat

-0.07

relevant

-0.07

_Msk

-0.06

BO

-0.06

sis

-0.06

 myth

-0.06

ová

-0.06

 v�

-0.06

LOSE

-0.06

POSITIVE LOGITS

cam

0.07

 Column

0.06

.can

0.06

-kind

0.06

 comprehensive

0.06

 translates

0.06

 amigo

0.06

mentioned

0.06

	read

0.06

_CM

0.06

Activations Density 0.010%

can

The neuron never fires—it doesn’t pick up on any pattern in the text and remains inactive.

No Comments

No Known Activations