INDEX

Explanations

Updating information

np_max-act · gemini-2.0-flash

The neuron activates on instructions or prompts to update or change personal, billing, or account information.

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

,None

-0.07

reation

-0.07

exion

-0.07

 SIDE

-0.06

sections

-0.06

 Rebels

-0.06

 masses

-0.06

atement

-0.06

flip

-0.06

_tel

-0.06

POSITIVE LOGITS

 getSupportActionBar

0.07

审核

0.07

ฝ

0.07

 elic

0.06

 UIScrollView

0.06

|.

0.06

<TSource

0.06

<Field

0.06

(HWND

0.06

?,

0.06

Activations Density 0.023%

Updating information

The neuron activates on instructions or prompts to update or change personal, billing, or account information.

No Comments

No Known Activations