INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

This neuron activates on items in structured lists or headings—e.g. standalone list entries, section titles, or bullet‐style labels.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 preschool

-0.07

 servic

-0.07

statement

-0.07

 الاجتماع

-0.06

 IndexError

-0.06

กรม

-0.06

via

-0.06

 причин

-0.06

subscription

-0.06

-looking

-0.06

POSITIVE LOGITS

."','".$

0.06

 incontr

0.06

 shipment

0.06

 sectional

0.06

Atlantic

0.06

 analyst

0.06

 темп

0.06

 TRAN

0.06

 alcan

0.06

ラス

0.05

Activations Density 0.071%

punctuation

This neuron activates on items in structured lists or headings—e.g. standalone list entries, section titles, or bullet‐style labels.

No Comments

No Known Activations