INDEX

Explanations

phrases that suggest the existence of potential implications or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 either

-0.19

 indeed

-0.18

either

-0.18

 both

-0.18

 bÃ¥de

-0.18

 first

-0.16

 Either

-0.15

æĹ¢

-0.15

 accordingly

-0.15

both

-0.15

POSITIVE LOGITS

 other

0.26

 also

0.24

 equally

0.24

other

0.24

also

0.22

 another

0.22

Also

0.20

 otras

0.19

 Ã©galement

0.19

 ALSO

0.19

Activations Density 0.518%

phrases that suggest the existence of potential implications or outcomes

No Comments

No Known Activations