INDEX

Explanations

and

np_max-act · gemini-2.0-flash

The neuron fires on numeric tokens—especially decimal numbers and measurement values—in the text.

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

polator

-0.07

整

-0.06

ملة

-0.06

ostí

-0.06

.Tree

-0.06

 September

-0.06

 duro

-0.06

(isolate

-0.06

FLOAT

-0.06

avity

-0.06

POSITIVE LOGITS

 Osman

0.07

rgan

0.06

ุด

0.06

	Send

0.06

IKE

0.06

нг

0.06

/*/

0.06

_pic

0.06

 Coco

0.06

ru

0.06

Activations Density 0.040%

and

The neuron fires on numeric tokens—especially decimal numbers and measurement values—in the text.

No Comments

No Known Activations