INDEX

Explanations

references to usage scenarios and requirements related to services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

avaÅŁ

-0.15

ouched

-0.15

Î³Î¿

-0.15

emony

-0.15

modifiable

-0.14

uja

-0.14

ioned

-0.14

auge

-0.14

lÃ¤

-0.14

 gÃ¶n

-0.13

POSITIVE LOGITS

multiple

0.19

Multiple

0.18

iley

0.18

 multiple

0.18

eur

0.16

 Multiple

0.15

izin

0.14

DAQ

0.14

ext

0.14

ä¹¡

0.14

Activations Density 0.012%

references to usage scenarios and requirements related to services or products

No Comments

No Known Activations