INDEX

Explanations

terms related to speed and efficiency in processes or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Continued

-0.17

nage

-0.15

 Budget

-0.15

-budget

-0.15

vla

-0.14

.listen

-0.14

uele

-0.14

 prolong

-0.14

 budget

-0.13

canf

-0.13

POSITIVE LOGITS

 pace

0.33

 paced

0.31

-paced

0.30

 turnaround

0.26

éĢŁåº¦

0.26

idious

0.25

 chÃ³ng

0.24

 Pace

0.23

paced

0.23

 speeds

0.22

Activations Density 0.105%

terms related to speed and efficiency in processes or services

No Comments

No Known Activations