INDEX

Explanations

navigation elements and links in a web document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

aman

-0.15

 Hind

-0.15

 Ð·Ð°Ðº

-0.15

 æĬķç¨¿

-0.15

lightbox

-0.14

enti

-0.14

bjerg

-0.14

vinc

-0.14

 cult

-0.14

vens

-0.14

POSITIVE LOGITS

anky

0.16

 Marian

0.15

 Carpenter

0.14

 ÑĢÐµÐ¶

0.14

Ð»ÐºÐ¸

0.14

ÑĮÑı

0.14

aria

0.14

anker

0.13

BITS

0.13

ower

0.13

Activations Density 0.152%

navigation elements and links in a web document

No Comments

No Known Activations