INDEX

Explanations

references to new products or offerings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ctype

-0.19

bras

-0.16

peria

-0.16

ÃŃk

-0.15

é³´

-0.15

Ã¤Ã¤n

-0.15

otate

-0.15

.ua

-0.15

oice

-0.15

iker

-0.15

POSITIVE LOGITS

 span

0.37

-span

0.34

 spanking

0.32

span

0.30

 Span

0.28

ishing

0.27

-new

0.25

 spans

0.25

enburg

0.24

ished

0.23

Activations Density 0.006%

references to new products or offerings

No Comments

No Known Activations