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

ENSE

-0.16

sdale

-0.15

iores

-0.15

lio

-0.15

orca

-0.14

Éµ

-0.14

Ãª

-0.14

 Gast

-0.14

orate

-0.14

POSITIVE LOGITS

zion

0.15

Ð¾Ð²Ð¸

0.14

attern

0.14

oldt

0.14

JUnit

0.14

isper

0.14

iddy

0.13

ypi

0.13

 pione

0.13

uler

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.