INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ngo

-0.16

orre

-0.15

BEL

-0.14

utin

-0.14

smarty

-0.14

iÅ¡

-0.14

_EVT

-0.14

imeline

-0.14

ãĥ

-0.14

ÐµÐ²Ð¸Ñĩ

-0.14

POSITIVE LOGITS

0.15

 midd

0.15

odian

0.14

aines

0.13

 Pascal

0.13

 standart

0.13

agon

0.13

 than

0.13

tuk

0.13

 dart

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.