INDEX

Explanations

references to influential figures and their contributions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

raz

-0.14

å®ŀåľ¨

-0.14

 Muss

-0.14

Uk

-0.14

dn

-0.13

ÑģÐ»Ð¸

-0.13

ÐµÑĢÐ¸Ð¼

-0.13

/latest

-0.13

ron

-0.13

Ph

-0.12

POSITIVE LOGITS

-alist

0.15

plusplus

0.14

astle

0.14

solete

0.13

VOID

0.13

REFERRED

0.13

verity

0.13

istrovstvÃŃ

0.13

ucht

0.13

agua

0.13

Activations Density 0.728%

references to influential figures and their contributions in various contexts

No Comments

No Known Activations