INDEX

Explanations

brackets

np_max-act · gemini-2.0-flash

The neuron activates on in-text reference or citation markers—i.e. bracketed numerical or alphanumerical citations.

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

 shows

-0.08

Pic

-0.07

com

-0.07

CE

-0.07

unknown

-0.06

 prospect

-0.06

likelihood

-0.06

б

-0.06

 tedbir

-0.06

POSITIVE LOGITS

 بـ

0.08

.newBuilder

0.07

>Edit

0.06

(QObject

0.06

 여러

0.06

 नए

0.06

ๆ

0.06

 aspir

0.06

 Bind

0.06

.depth

0.06

Activations Density 0.047%

brackets

The neuron activates on in-text reference or citation markers—i.e. bracketed numerical or alphanumerical citations.

No Comments

No Known Activations