INDEX

Explanations

Runtime

np_max-act · gemini-2.0-flash

The neuron fires on the literal token “Runtime” (i.e. it detects occurrences of the word “Runtime”).

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

----</

-0.07

 mocker

-0.06

.Keyboard

-0.06

GAR

-0.06

Logs

-0.06

_stock

-0.06

.statistics

-0.06

 avant

-0.05

POSITIVE LOGITS

IMITER

0.07

播放

0.07

 relocation

0.06

ウス

0.06

 pushes

0.06

ционной

0.06

宫

0.06

BACKGROUND

0.06

IENTATION

0.06

ฤด

0.06

Activations Density 0.001%

Runtime

The neuron fires on the literal token “Runtime” (i.e. it detects occurrences of the word “Runtime”).

No Comments

No Known Activations