INDEX

Explanations

words related to user interface actions and interactions with technology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¼ł

-0.19

 klik

-0.17

Mouse

-0.16

 mouse

-0.15

alink

-0.15

ogl

-0.14

 MOUSE

-0.14

mouseover

-0.14

 Wings

-0.14

 laptops

-0.14

POSITIVE LOGITS

sw

0.36

 gesture

0.33

tap

0.32

 Gest

0.32

 gestures

0.32

 gest

0.30

-sw

0.30

 swipe

0.29

Tap

0.28

Tap

0.28

Activations Density 0.058%

words related to user interface actions and interactions with technology

No Comments

No Known Activations