INDEX

Explanations

statistical references and numerical data related to performance or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

adge

-0.20

illy

-0.16

leton

-0.15

reet

-0.15

 Legend

-0.15

ziel

-0.15

æŀľ

-0.14

*>::

-0.14

 Macro

-0.14

ÅĻe

-0.14

POSITIVE LOGITS

ething

0.16

Ð°Ð»Ð¾Ð³

0.15

asso

0.15

wert

0.15

oker

0.15

èĪĮ

0.14

agit

0.14

vaÅ¾

0.14

teg

0.14

AQ

0.14

Activations Density 0.172%

statistical references and numerical data related to performance or outcomes

No Comments

No Known Activations