INDEX

Explanations

-bottom

np_max-act · gemini-2.0-flash

This neuron never activates on any token in these CSS/SCSS examples, i.e. it isn’t detecting any pattern here.

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

云

-0.07

 shipment

-0.06

 Milk

-0.06

цеп

-0.06

ador

-0.06

 invade

-0.06

 Hide

-0.06

 confort

-0.06

Cache

-0.06

CAL

-0.06

POSITIVE LOGITS

-pr

0.07

 paddingBottom

0.07

บาล

0.07

 jednoduch

0.07

elson

0.06

族自治

0.06

-close

0.06

_triangle

0.06

.classList

0.06

プリ

0.06

Activations Density 0.001%

-bottom

This neuron never activates on any token in these CSS/SCSS examples, i.e. it isn’t detecting any pattern here.

No Comments

No Known Activations