INDEX

Explanations

references to economic indicators and market performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 hÃ¢l

-0.16

Å¥

-0.15

cakes

-0.15

 KÃ¶y

-0.15

å¶

-0.15

Äįan

-0.14

åħ¨åĽ½

-0.14

itou

-0.14

æ½®

-0.14

irma

-0.14

POSITIVE LOGITS

 bond

0.33

Fed

0.31

 markets

0.28

equ

0.28

 bonds

0.26

 stocks

0.26

Fed

0.26

 stock

0.25

 Bond

0.24

 Bonds

0.24

Activations Density 0.111%

references to economic indicators and market performance

No Comments

No Known Activations