INDEX

Explanations

15

np_max-act · gemini-2.0-flash

The neuron primarily activates on in-text citation markers (e.g. numbered or tagged references in brackets).

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

	Public

-0.07

кое

-0.07

나라

-0.06

’de

-0.06

(dtype

-0.06

 πλη

-0.06

_OPEN

-0.06

σσότε

-0.06

sexy

-0.06

 однако

-0.06

POSITIVE LOGITS

↵    ↵↵

0.06

↵

0.06

 Dates

0.06

 Britann

0.06

state

0.06

zipcode

0.06

>n

0.05

 พล

0.05

.leadingAnchor

0.05

bike

0.05

Activations Density 0.014%

15

The neuron primarily activates on in-text citation markers (e.g. numbered or tagged references in brackets).

No Comments

No Known Activations