INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

atz

-0.20

ÑĢÐ°ÑħÐ¾Ð²

-0.15

arra

-0.15

 Ø·Ø±Ùģ

-0.14

era

-0.14

quil

-0.14

.Character

-0.14

/GPL

-0.14

 (*((

-0.13

pler

-0.13

POSITIVE LOGITS

ØµØ§Øª

0.15

ayout

0.15

istrovstvÃŃ

0.14

obo

0.14

ÐµÐ¼Ñĥ

0.14

uner

0.14

ruptions

0.14

EIF

0.14

zv

0.14

uger

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.