INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

vasive

-0.15

elize

-0.15

ascimento

-0.15

iks

-0.14

tent

-0.14

Ð²Ð¸Ñī

-0.14

.dec

-0.14

nect

-0.14

arella

-0.14

StringEncoding

-0.14

POSITIVE LOGITS

 Dodd

0.16

infeld

0.15

ulp

0.15

uld

0.15

ignon

0.15

indow

0.14

allen

0.14

 Kaplan

0.14

kening

0.14

 Black

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.