INDEX

Explanations

numerical values, especially those associated with mathematical equations and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

anova

-0.16

anou

-0.16

gom

-0.16

ing

-0.15

ACHI

-0.15

cess

-0.15

 Exped

-0.15

kara

-0.15

ansible

-0.14

ÑĩÐµÐ¼

-0.14

POSITIVE LOGITS

 Wort

0.14

_atts

0.14

ä¹İ

0.14

Zot

0.14

/free

0.14

 Sick

0.13

TimeString

0.13

/*č↵

0.13

Activations Density 0.037%

numerical values, especially those associated with mathematical equations and notations

No Comments

No Known Activations