INDEX

Explanations

mathematical expressions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

éĦ

-0.16

Ð°ÐºÐ¾Ð½

-0.15

ugo

-0.15

\Mapping

-0.15

chwitz

-0.14

 IsValid

-0.14

 éĦ

-0.14

alaria

-0.14

å·¡

-0.14

engin

-0.14

POSITIVE LOGITS

 half

0.18

ahat

0.16

inch

0.15

ouch

0.15

vic

0.14

#/

0.14

iras

0.14

apult

0.14

half

0.14

 fame

0.14

Activations Density 0.062%

mathematical expressions and equations

No Comments

No Known Activations