INDEX

Explanations

references to stocks and stock market terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ÑģÑĤÑĢÐ¾Ð¹

-0.14

ignum

-0.14

naires

-0.14

andbox

-0.14

.intellij

-0.14

çĵľ

-0.14

ugs

-0.14

ost

-0.14

Ike

-0.14

aw

-0.14

POSITIVE LOGITS

pile

0.42

holm

0.28

piler

0.26

dale

0.25

holders

0.25

holder

0.24

PILE

0.23

taking

0.21

tober

0.20

ton

0.20

Activations Density 0.022%

references to stocks and stock market terminology

No Comments

No Known Activations