INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

çīĩ

-0.18

 pred

-0.15

 Virgin

-0.14

Vir

-0.14

 Governor

-0.13

 surrogate

-0.13

oka

-0.13

ãĤıãģĳ

-0.13

added

-0.13

 acquisitions

-0.13

POSITIVE LOGITS

ëı

0.16

lus

0.15

unan

0.15

.GraphicsUnit

0.15

heet

0.14

slot

0.14

 Wein

0.14

azo

0.14

ropdown

0.14

inka

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.