INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ips

-0.17

ureau

-0.15

dd

-0.14

owitz

-0.14

mites

-0.14

otu

-0.14

-Ta

-0.14

ditor

-0.14

-less

-0.14

arn

-0.14

POSITIVE LOGITS

 âģ

0.16

czy

0.15

LOBAL

0.15

ðŁ

0.15

 ðŁ

0.15

 autogenerated

0.15

ImageData

0.15

warz

0.15

 Hence

0.14

 Archer

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.