INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

cff

-0.15

Ð²Ð¾ÑĢ

-0.15

kur

-0.15

ÐĤ

-0.15

strup

-0.15

oma

-0.14

 ifndef

-0.14

inition

-0.13

 isolation

-0.13

POSITIVE LOGITS

lake

0.15

rana

0.15

uzzi

0.14

/fixtures

0.14

uzzle

0.14

InnerText

0.14

phinx

0.14

yii

0.14

 outs

0.13

xes

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.