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

 Balls

-0.16

vale

-0.15

tings

-0.15

 Mechan

-0.15

urs

-0.14

Į

-0.14

 Motor

-0.14

 Trit

-0.14

stre

-0.14

 balls

-0.14

POSITIVE LOGITS

cky

0.15

_lineno

0.15

.twig

0.15

ldc

0.14

rogen

0.14

 Rare

0.14

ìĦł

0.14

 Humanity

0.14

uong

0.14

 Sanford

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.