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

Ã©ment

-0.15

alat

-0.15

 policymakers

-0.14

ÅĻÃŃzenÃŃ

-0.14

 Serialized

-0.14

 wiÄĻc

-0.13

ÏĥÎ¹Î±

-0.13

æī¶

-0.13

pcs

-0.13

uka

-0.13

POSITIVE LOGITS

wa

0.17

opt

0.15

kok

0.14

 auto

0.14

,)↵

0.14

anke

0.14

 lone

0.14

actory

0.13

mediate

0.13

kie

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.