INDEX

Explanations

name

np_max-act · gemini-2.0-flash

The neuron fires on tokens introducing a place’s name-or-etymology section (e.g. “Name,” “origin of the name,” “meaning,” 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-summary

-0.06

্

-0.06

_validator

-0.06

Sy

-0.06

 emphasized

-0.06

 dirty

-0.06

 rẻ

-0.06

_crc

-0.06

｛

-0.06

Ri

-0.06

POSITIVE LOGITS

Toolbar

0.06

 snatch

0.06

 setTimeout

0.06

 cerc

0.06

 Syntax

0.06

 HDMI

0.06

angles

0.06

 سن

0.06

 Torrent

0.06

 спіл

0.06

Activations Density 0.026%

name

The neuron fires on tokens introducing a place’s name-or-etymology section (e.g. “Name,” “origin of the name,” “meaning,” etc.).

No Comments

No Known Activations