INDEX

Explanations

mathematical terms and definitions, particularly those related to functions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

urat

-0.17

stÃŃ

-0.15

 Latest

-0.15

amoto

-0.15

//{{

-0.15

åĩĨ

-0.14

 Crowley

-0.14

enties

-0.14

_Meta

-0.14

enville

-0.14

POSITIVE LOGITS

 Desk

0.17

ughters

0.15

 intern

0.14

MLE

0.14

asley

0.14

ssa

0.13

Intern

0.13

Ð¾Ð¶Ð´ÐµÐ½Ð¸Ðµ

0.13

 Intern

0.13

-panel

0.13

Activations Density 0.524%

mathematical terms and definitions, particularly those related to functions and equations

No Comments

No Known Activations