INDEX

Explanations

numerical values and mentions of organizations or team structures

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

elsen

-0.15

dÃ¼l

-0.15

 spread

-0.14

inesis

-0.14

irs

-0.14

ifen

-0.14

 åĺ

-0.14

Spread

-0.14

 Spread

-0.13

uzzi

-0.13

POSITIVE LOGITS

 both

0.31

 respectively

0.31

åĪĨåĪ«

0.30

two

0.28

both

0.27

ä¸¤ä¸ª

0.26

Nos

0.24

two

0.23

 BOTH

0.23

_both

0.23

Activations Density 0.399%

numerical values and mentions of organizations or team structures

No Comments

No Known Activations