INDEX

Explanations

references to digital object identifiers (DOIs) in academic documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.18

Ade

-0.17

ãĤ·ãĤ§

-0.16

_Desc

-0.15

oucher

-0.15

·

-0.14

wu

-0.14

ornado

-0.14

ixon

-0.14

 Ð¿Ð¸ÑĤ

-0.14

POSITIVE LOGITS

eland

0.17

-alist

0.15

alter

0.15

 noreferrer

0.14

linky

0.14

DataTask

0.13

.addObserver

0.13

ÐµÐ»ÐµÐ½Ð¸Ñı

0.13

ey

0.13

_extensions

0.13

Activations Density 0.009%

references to digital object identifiers (DOIs) in academic documents

No Comments

No Known Activations