INDEX

Explanations

financial metrics and corporate activities related to losses and impairments

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

anut

-0.17

----------------------------------------------------------------------

-0.16

 Ekon

-0.15

ieber

-0.15

azers

-0.15

 MÃľ

-0.15

 scre

-0.14

REATE

-0.14

iel

-0.14

gger

-0.14

POSITIVE LOGITS

 Company

0.19

 earnings

0.18

NYSE

0.18

 Separ

0.16

ovaly

0.15

 Chairman

0.15

 Borg

0.15

 fiscal

0.15

earn

0.15

 ÐļÐ¾ÑģÑĤ

0.15

Activations Density 0.494%

financial metrics and corporate activities related to losses and impairments

No Comments

No Known Activations