INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.18

-0.16

zing

-0.15

ÐµÑģÐ°

-0.15

iyat

-0.15

.mm

-0.14

warf

-0.14

-0.13

POSITIVE LOGITS

 Raven

0.23

 Boeh

0.20

-Co

0.19

wich

0.18

 village

0.18

 Gregory

0.18

Co

0.18

idia

0.16

Greg

0.16

SCO

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.