INDEX

Explanations

terminology related to enterprise data management and analytics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

COVID

-0.16

="__

-0.15

bios

-0.15

signature

-0.15

 COVID

-0.15

 covid

-0.15

Tele

-0.14

tele

-0.14

.Magenta

-0.14

trainer

-0.14

POSITIVE LOGITS

ad

0.23

 Campaign

0.22

 Agency

0.22

 agency

0.21

 campaigns

0.21

 campaign

0.21

 Attribution

0.21

Agency

0.20

 attribution

0.20

 agencies

0.20

Activations Density 0.001%

terminology related to enterprise data management and analytics

No Comments

No Known Activations