INDEX

Explanations

metrics related to stock performance and business analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

conversation

-0.16

 branch

-0.16

/null

-0.16

 conversation

-0.15

branch

-0.14

 Capitals

-0.14

/Branch

-0.14

esiz

-0.14

igner

-0.14

cek

-0.13

POSITIVE LOGITS

 stock

0.25

 shares

0.25

 stocks

0.23

 Shares

0.21

-stock

0.20

stock

0.19

 STOCK

0.19

èĤ¡

0.17

Nas

0.17

shares

0.17

Activations Density 0.088%

metrics related to stock performance and business analysis

No Comments

No Known Activations