INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

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

ologue

-0.16

ouden

-0.15

ntax

-0.15

FromClass

-0.15

 ejac

-0.14

objc

-0.14

Mej

-0.14

PathComponent

-0.14

holm

-0.13

Sibling

-0.13

POSITIVE LOGITS

ayo

0.18

okers

0.18

uth

0.16

hand

0.15

ely

0.14

oker

0.14

rc

0.14

isha

0.13

gg

0.13

em

0.13

Activations Density 1.679%

No Comments

No Known Activations