INDEX

Explanations

references to hedge funds and financial institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 probation

-0.15

antz

-0.15

mol

-0.15

 nett

-0.14

.gdx

-0.14

spor

-0.13

ipro

-0.13

 Ð³ÑĥÐ±

-0.13

 spare

-0.13

 retrieved

-0.13

POSITIVE LOGITS

 Partners

0.32

 Capital

0.28

 Holding

0.28

LP

0.28

GP

0.27

 Fund

0.27

 Funds

0.25

 Acquisition

0.25

 Management

0.25

 Advisors

0.25

Activations Density 0.152%

references to hedge funds and financial institutions

No Comments

No Known Activations