INDEX

Explanations

mathematical symbols and variables used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

å¤§åħ¨

-0.15

 ÏħÏĢÎ¬ÏģÏĩÎ¿ÏħÎ½

-0.15

II

-0.14

ÑģÑĤÐ¸Ð½

-0.14

Î½ÏĮ

-0.14

 ÎĶ

-0.14

adece

-0.14

Î¼Î¹Ïĥ

-0.14

III

-0.14

Big

-0.14

POSITIVE LOGITS

alpha

0.40

beta

0.34

 alpha

0.32

theta

0.32

lambda

0.32

gamma

0.32

xi

0.28

eta

0.28

nu

0.27

 beta

0.27

Activations Density 0.209%

mathematical symbols and variables used in equations

No Comments

No Known Activations