INDEX

Explanations

code snippets and HTML elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

alsa

-0.17

inge

-0.16

etti

-0.16

Keeper

-0.15

pron

-0.15

 pron

-0.14

(BitConverter

-0.14

uci

-0.14

&t

-0.14

#region

-0.13

POSITIVE LOGITS

endregion

0.26

@endforeach

0.26

 esac

0.24

endforeach

0.24

{/

0.23

 glEnd

0.23

 endregion

0.23

 endforeach

0.23

 endif

0.23

.END

0.20

Activations Density 0.100%

code snippets and HTML elements

No Comments

No Known Activations