INDEX

Explanations

concepts related to market analysis and stock performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ums

-0.15

antino

-0.15

LOPT

-0.15

oger

-0.14

ancode

-0.14

elik

-0.14

modes

-0.14

bart

-0.14

utas

-0.14

sher

-0.13

POSITIVE LOGITS

 stocks

0.41

stocks

0.30

 shares

0.29

 Stocks

0.29

 stock

0.28

 companies

0.26

-stock

0.25

 names

0.24

 plays

0.23

 beaten

0.23

Activations Density 0.096%

concepts related to market analysis and stock performance

No Comments

No Known Activations