INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ule

-0.15

Vac

-0.15

antis

-0.14

anova

-0.14

alc

-0.14

è´£

-0.13

artz

-0.13

traction

-0.13

ut

-0.13

POSITIVE LOGITS

uess

0.19

/uploads

0.16

IMO

0.15

ipur

0.15

atik

0.14

 author

0.14

ContentPane

0.14

ovit

0.14

udi

0.13

Narrated

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.