INDEX

Explanations

financial metrics and stock performance indicators

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

ãĥªãĤ«

-0.15

ta

-0.15

esiz

-0.15

Ð¼ÐµÑĩ

-0.14

bor

-0.14

iset

-0.14

RACT

-0.14

-0.13

Reach

-0.13

POSITIVE LOGITS

 earnings

0.39

earn

0.31

EPS

0.29

 Guidance

0.28

 guidance

0.28

EPS

0.26

 revenue

0.26

 earning

0.24

eps

0.24

 earn

0.23

Activations Density 0.117%

financial metrics and stock performance indicators

No Comments

No Known Activations