INDEX

Explanations

phrases related to user functionalities and actions in software applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

sanitize

-0.16

 succeed

-0.15

 sanitize

-0.13

 Canter

-0.13

igure

-0.13

 Stevenson

-0.13

ritel

-0.13

.scalablytyped

-0.13

ucceed

-0.13

oming

-0.13

POSITIVE LOGITS

 view

0.27

 easily

0.26

view

0.23

View

0.23

 View

0.23

-view

0.23

 viewed

0.22

 export

0.19

 Easily

0.19

 viewing

0.18

Activations Density 0.195%

phrases related to user functionalities and actions in software applications

No Comments

No Known Activations