INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

unks

-0.16

alon

-0.15

lett

-0.14

ë¶ģ

-0.14

oard

-0.14

amoto

-0.14

atch

-0.14

RTL

-0.14

au

-0.14

 static

-0.14

POSITIVE LOGITS

kees

0.16

æĸ¹

0.15

à¸ķà¸£

0.14

ecta

0.14

PLICIT

0.14

 Marble

0.14

 atol

0.14

Ã¨ne

0.14

 barr

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.