INDEX

Explanations

terminology related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ovit

-0.16

lox

-0.16

arten

-0.15

.scalajs

-0.14

hang

-0.14

 ØªØŃØµÛĮÙĦ

-0.14

kok

-0.14

 Spect

-0.14

laus

-0.14

printer

-0.14

POSITIVE LOGITS

 Apex

0.31

 apex

0.30

 Lightning

0.26

Aura

0.26

 lightning

0.25

 Aura

0.24

aura

0.24

 aura

0.23

{!

0.23

 Account

0.23

Activations Density 0.002%

terminology related to programming and data structures

No Comments

No Known Activations