INDEX

Explanations

business-related terminology and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

iqueta

-0.15

 Patreon

-0.14

tvb

-0.14

odka

-0.14

.DataVisualization

-0.14

íİ¸

-0.14

onymous

-0.13

ë¥ĺ

-0.13

gili

-0.13

ooting

-0.13

POSITIVE LOGITS

BPM

0.29

BFS

0.27

 offshore

0.26

 outsourcing

0.25

 Outs

0.25

 Infos

0.24

IT

0.23

 Nass

0.22

Infos

0.22

 delivery

0.21

Activations Density 0.024%

business-related terminology and metrics

No Comments

No Known Activations