INDEX

Explanations

references to quantities or amounts related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

bons

-0.15

amer

-0.15

ccount

-0.15

warts

-0.14

.grp

-0.14

hores

-0.14

hire

-0.13

Ð½Ð¸ÑģÑĤ

-0.13

formed

-0.13

ource

-0.13

POSITIVE LOGITS

ing

0.32

/type

0.27

 spent

0.26

/types

0.23

spent

0.22

_paid

0.20

 payable

0.20

 invested

0.20

 needed

0.20

 expended

0.20

Activations Density 0.045%

references to quantities or amounts related to various subjects

No Comments

No Known Activations

references to quantities or amounts related to various subjects

No Comments

No Known Activations