INDEX

Explanations

commands related to the inclusion of graphics or images in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ence

-0.14

uli

-0.14

Ã¥de

-0.14

Ø¨Ø§Øª

-0.14

etimes

-0.14

 personals

-0.13

à¸²à¸ĩ

-0.13

olas

-0.13

ãģ°

-0.13

ycop

-0.13

POSITIVE LOGITS

0.16

prm

0.15

utar

0.15

Ø§Ø²Ùĩ

0.14

erval

0.14

uw

0.14

appa

0.14

resco

0.14

¥¿

0.14

ecies

0.14

Activations Density 0.017%

commands related to the inclusion of graphics or images in a document

No Comments

No Known Activations