INDEX

Explanations

financial metrics and performance indicators related to companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Rip

-0.16

heel

-0.15

quete

-0.14

 Garrison

-0.14

inta

-0.14

ric

-0.13

rate

-0.13

RIC

-0.13

esser

-0.13

ansk

-0.13

POSITIVE LOGITS

 posted

0.36

 recorded

0.32

 posting

0.32

 reporting

0.32

 reported

0.29

posted

0.28

 recording

0.28

 posts

0.28

 Reporting

0.26

reported

0.26

Activations Density 0.071%

financial metrics and performance indicators related to companies

No Comments

No Known Activations