INDEX

Explanations

mathematical terms and notations related to equations and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

á»ĥn

-0.14

OOT

-0.14

ajor

-0.14

ovie

-0.13

enek

-0.13

lav

-0.13

aliz

-0.13

.Throw

-0.13

íģ

-0.13

áº¥p

-0.13

POSITIVE LOGITS

 derivative

0.19

 sensit

0.18

 differentiation

0.18

 sensitivity

0.18

 derivatives

0.17

 Barg

0.16

 differential

0.16

adients

0.16

 differentiated

0.16

 differentiate

0.15

Activations Density 0.097%

mathematical terms and notations related to equations and functions

No Comments

No Known Activations