INDEX

Explanations

references to literary figures or elements related to literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

undy

-0.16

ÑĮÐºÐ¾

-0.15

esda

-0.14

ecome

-0.14

alez

-0.14

ez

-0.13

aic

-0.13

ombat

-0.13

Ð¾ÑĩÐºÐ¸

-0.12

icode

-0.12

POSITIVE LOGITS

oki

0.14

adlo

0.14

kinci

0.14

Î»Î¿Î¹

0.13

 nues

0.13

han

0.12

izo

0.12

âĢ¦the

0.12

.createSequentialGroup

0.12

xBB

0.12

Activations Density 0.253%

references to literary figures or elements related to literature

No Comments

No Known Activations