INDEX

Explanations

punctuations and sentence boundaries

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

cess

-0.15

bs

-0.14

udas

-0.14

avo

-0.14

aa

-0.14

åĸĦ

-0.14

lag

-0.13

end

-0.13

tr

-0.13

POSITIVE LOGITS

bens

0.16

_mC

0.16

_mB

0.16

_mD

0.15

alach

0.15

ÑĥÑĢÐ½

0.14

_tC

0.14

 konkrÃ©t

0.14

infinity

0.14

rada

0.14

Activations Density 0.352%

punctuations and sentence boundaries

No Comments

No Known Activations