INDEX

Explanations

special characters or symbols often used in document formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

arcy

-0.16

ktor

-0.15

ync

-0.15

auc

-0.14

stav

-0.14

èĢĢ

-0.14

iring

-0.14

 Tata

-0.14

ä¿Ĺ

-0.14

igner

-0.14

POSITIVE LOGITS

lus

0.17

oji

0.16

utex

0.14

arrison

0.14

Reusable

0.14

 Hutchinson

0.14

awe

0.14

UU

0.13

">//

0.13

ogh

0.13

Activations Density 0.006%

special characters or symbols often used in document formatting

No Comments

No Known Activations