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

chk

-0.15

Fol

-0.15

 ought

-0.14

 Picture

-0.14

istra

-0.13

 Austr

-0.13

 Holl

-0.13

 anybody

-0.13

 hence

-0.13

hol

-0.13

POSITIVE LOGITS

 Transmit

0.18

 transmit

0.16

.DropTable

0.15

 ÙĨØ§ØŃ

0.15

 transmitting

0.15

_errno

0.15

 Transmission

0.14

 fucks

0.14

\CMS

0.14

Transmission

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.