INDEX

Explanations

expressions indicating warnings or restrictions regarding sensitive content

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

SystemService

-0.16

anko

-0.16

elay

-0.15

el

-0.15

Lau

-0.15

ãģ¤ãģ¶

-0.15

met

-0.14

ins

-0.14

POSITIVE LOGITS

infeld

0.19

#ae

0.17

arga

0.17

ucha

0.16

Ã¤ter

0.16

UDGE

0.16

locker

0.16

_terminal

0.15

axe

0.15

ULER

0.15

Activations Density 0.186%

expressions indicating warnings or restrictions regarding sensitive content

No Comments

No Known Activations