INDEX

Explanations

references to academic authors and their works in mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Å¡k

-0.16

araoh

-0.16

alach

-0.15

ynes

-0.15

pto

-0.15

asures

-0.15

.SM

-0.15

ÑģÐ¸Ð¼

-0.15

ãĤ¤ãĥī

-0.14

uant

-0.14

POSITIVE LOGITS

_{}

0.15

å¡ļ

0.14

 Ð³ÑĥÐ±

0.14

æĽ

0.14

ko

0.14

umlu

0.13

Îµ

0.13

 INLINE

0.13

ë¡Ŀ

0.13

ENTA

0.13

Activations Density 0.013%

references to academic authors and their works in mathematical contexts

No Comments

No Known Activations