INDEX

Explanations

phrases that refer to the financial implications or conclusions in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

erken

-0.18

ÙħØ§

-0.16

ever

-0.16

umber

-0.16

zin

-0.15

zn

-0.15

ÐµÐ³Ð¾ÑĢ

-0.15

onne

-0.15

vÃ¤

-0.14

IENT

-0.14

POSITIVE LOGITS

most

0.24

bottom

0.22

 Bottom

0.22

/top

0.21

 bottom

0.20

-bottom

0.20

(bottom

0.20

.Bottom

0.19

-most

0.19

BOTTOM

0.18

Activations Density 0.017%

phrases that refer to the financial implications or conclusions in a text

No Comments

No Known Activations