INDEX

Explanations

website excerpts

np_max-act · gemini-2.0-flash

This neuron fires on UI navigation labels and menu/header tokens (e.g. site menu items and interface controls).

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

protocol

-0.07

Book

-0.07

-ref

-0.07

 pear

-0.07

éli

-0.07

-core

-0.06

anı

-0.06

Invoker

-0.06

 Fulton

-0.06

Over

-0.06

POSITIVE LOGITS

 Voters

0.06

PCM

0.06

_trigger

0.06

 Clears

0.06

stitute

0.06

 قط

0.06

();"

0.06

-Allow

0.06

 Lastly

0.06

=train

0.06

Activations Density 0.042%

website excerpts

This neuron fires on UI navigation labels and menu/header tokens (e.g. site menu items and interface controls).

No Comments

No Known Activations