INDEX

Explanations

IT infrastructure/services

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the product name “Microsoft 365” (often broken into tokens like “M” and “365”).

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

 Grain

-0.07

pure

-0.07

plans

-0.07

 Potion

-0.06

IEEE

-0.06

 traps

-0.06

.AutoSizeMode

-0.06

Sea

-0.06

 فقط

-0.06

fro

-0.06

POSITIVE LOGITS

 док

0.06

하신

0.06

_util

0.06

 буду

0.06

ществ

0.06

Ang

0.06

Mods

0.06

=>

0.06

ALLERY

0.06

 zeroes

0.06

Activations Density 0.063%

IT infrastructure/services

The neuron activates on occurrences of the product name “Microsoft 365” (often broken into tokens like “M” and “365”).

No Comments

No Known Activations