INDEX

Explanations

technical specifications and guidelines related to coding standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ucci

-0.16

hiba

-0.15

 Patron

-0.15

lius

-0.14

icens

-0.13

enco

-0.13

elpers

-0.13

YS

-0.13

baugh

-0.13

buie

-0.13

POSITIVE LOGITS

ilde

0.15

apy

0.15

otech

0.15

lesia

0.15

indir

0.14

 Conserv

0.14

dish

0.14

ramid

0.14

ometer

0.14

indx

0.13

Activations Density 0.173%

technical specifications and guidelines related to coding standards

No Comments

No Known Activations