INDEX

Explanations

structured data related to object properties and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 packages

-0.15

eri

-0.15

-0.14

rael

-0.14

br

-0.14

et

-0.13

Orr

-0.13

={"/

-0.13

rop

-0.13

 Packages

-0.13

POSITIVE LOGITS

lÃŃÄį

0.14

 Rouge

0.14

stroy

0.14

ogne

0.14

ieux

0.14

advertisement

0.14

adÄ±ÄŁ

0.14

umb

0.13

otime

0.13

amac

0.13

Activations Density 0.142%

structured data related to object properties and attributes

No Comments

No Known Activations