INDEX

Explanations

gathering information

np_max-act · gemini-2.0-flash

The neuron fires on phrases that describe gathering or requiring user‐provided data (e.g. slot collection, form fields, “data required,” “collected,” etc.).

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

Í

-0.07

 idiots

-0.07

fld

-0.06

Д

-0.06

Υ

-0.06

 Parl

-0.06

.Serve

-0.06

PropTypes

-0.06

取

-0.06

�

-0.06

POSITIVE LOGITS

lady

0.07

Fun

0.07

 phận

0.06

 preferable

0.06

metrical

0.06

 acquire

0.06

 Azure

0.06

ydı

0.06

 Furthermore

0.06

.down

0.06

Activations Density 0.006%

gathering information

The neuron fires on phrases that describe gathering or requiring user‐provided data (e.g. slot collection, form fields, “data required,” “collected,” etc.).

No Comments

No Known Activations