INDEX

Explanations

references to notable individuals and academic concepts

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

uese

-0.16

esson

-0.15

 dele

-0.15

actly

-0.15

µľ

-0.14

creativecommons

-0.14

untas

-0.13

isoft

-0.13

undles

-0.13

 IMessage

-0.13

POSITIVE LOGITS

DMI

0.15

arlar

0.15

à¸¥

0.14

åĤ

0.14

.dense

0.14

Atlas

0.14

Lar

0.13

Ø±ÙĪÙħ

0.13

:".$

0.13

UZ

0.13

Activations Density 0.047%

references to notable individuals and academic concepts

No Comments

No Known Activations