INDEX

Explanations

references to economic data and indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ACE

-0.15

bib

-0.14

 vÄĽ

-0.14

odus

-0.14

åĻ

-0.14

arer

-0.14

ë²Ī

-0.14

utin

-0.13

abad

-0.13

radient

-0.13

POSITIVE LOGITS

ertino

0.15

nx

0.15

_SYN

0.14

áºŃu

0.14

_ENCODING

0.14

 knock

0.13

mn

0.13

 underlying

0.13

weeney

0.13

inx

0.12

Activations Density 0.060%

references to economic data and indicators

No Comments

No Known Activations