INDEX

Explanations

structured comments and documentation within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.framework

-0.15

/framework

-0.14

ume

-0.14

_IT

-0.14

ikip

-0.14

ows

-0.14

mic

-0.14

ivor

-0.14

aside

-0.14

/me

-0.13

POSITIVE LOGITS

ardy

0.17

zdy

0.15

iÃ©n

0.15

ksen

0.15

å²Ĺ

0.15

xFFF

0.15

ustin

0.14

RuntimeObject

0.14

RuleContext

0.14

ajes

0.14

Activations Density 0.005%

structured comments and documentation within code

No Comments

No Known Activations