INDEX

Explanations

financial metrics and analyses related to investment performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

agini

-0.16

onom

-0.15

cek

-0.14

_ary

-0.14

azo

-0.14

 Sharing

-0.14

å¯¸

-0.14

ä¸Ŀ

-0.14

 credits

-0.14

Credits

-0.14

POSITIVE LOGITS

 Guru

0.17

reeze

0.17

 beta

0.16

Beta

0.16

_beta

0.15

 tick

0.15

eps

0.15

_eps

0.15

 Beta

0.15

 debt

0.15

Activations Density 0.049%

financial metrics and analyses related to investment performance

No Comments

No Known Activations