INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arra

-0.18

 (*((

-0.17

ARR

-0.16

vise

-0.15

char

-0.14

clave

-0.14

 Ð¸Ñģ

-0.14

 anymore

-0.13

keley

-0.13

Fay

-0.13

POSITIVE LOGITS

obo

0.15

ayout

0.15

 Victor

0.15

/desktop

0.14

Enumerable

0.14

æľ¬

0.14

logfile

0.14

roup

0.14

 Wilkinson

0.14

renders

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.