INDEX

Explanations

references to rankings and awards in educational and organizational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Exped

-0.16

itte

-0.16

urovision

-0.15

á»Ľ

-0.15

irsch

-0.15

VIP

-0.15

ê¹

-0.15

eÄį

-0.14

.Metro

-0.14

iki

-0.14

POSITIVE LOGITS

éĢ¸

0.16

0.15

 Primitive

0.15

bill

0.14

.aw

0.14

 JpaRepository

0.14

by

0.14

ãĥªãĤ¹

0.14

fce

0.14

 enqu

0.14

Activations Density 0.003%

references to rankings and awards in educational and organizational contexts

No Comments

No Known Activations