INDEX

Explanations

mathematical symbols and notations 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

eltas

-0.19

acman

-0.16

ÙħØ§ÙĦ

-0.16

TOCOL

-0.15

iyas

-0.15

Kel

-0.15

ÑĸÐ´Ð½Ð¾

-0.15

Nap

-0.14

eras

-0.14

rupa

-0.14

POSITIVE LOGITS

irim

0.16

comings

0.15

AF

0.14

iset

0.14

HA

0.14

 Shaun

0.13

Ã¡

0.13

 Owens

0.13

Activations Density 0.100%

mathematical symbols and notations used in equations

No Comments

No Known Activations