INDEX

Explanations

terms and phrases related to the concept of "usage."

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

atura

-0.15

jac

-0.15

Zus

-0.14

esium

-0.14

itte

-0.14

ITTE

-0.14

iese

-0.14

isset

-0.14

otte

-0.13

castle

-0.13

POSITIVE LOGITS

ynos

0.16

gle

0.16

bd

0.15

unicorn

0.15

BD

0.15

ful

0.14

creenshot

0.14

 veter

0.14

ienie

0.14

ÐµÐ»ÐµÐ½Ð¸Ðµ

0.14

Activations Density 0.005%

terms and phrases related to the concept of "usage."

No Comments

No Known Activations