INDEX

Explanations

references to parameters in technical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

erman

-0.20

ress

-0.19

resses

-0.18

resse

-0.16

ear

-0.16

ermann

-0.16

arga

-0.16

 Ð½Ð°ÑģÐµÐ»ÐµÐ½Ð¸Ñı

-0.15

atel

-0.15

.LayoutParams

-0.15

POSITIVE LOGITS

etrize

0.26

ized

0.24

ater

0.23

etric

0.23

ter

0.22

ization

0.21

aters

0.21

etr

0.20

ised

0.20

ters

0.20

Activations Density 0.025%

references to parameters in technical or scientific contexts

No Comments

No Known Activations