INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

latlong

-0.14

 Brid

-0.14

ULK

-0.14

 chiáº¿u

-0.14

 Demon

-0.13

iable

-0.13

kker

-0.13

 stud

-0.13

ught

-0.13

POSITIVE LOGITS

ItemCount

0.16

ight

0.16

ismet

0.15

bÃŃ

0.14

edException

0.14

 Sext

0.14

ibi

0.14

CAF

0.13

Ã¢ng

0.13

IGHT

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.