INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Ð·Ð¼

-0.17

nig

-0.15

ORA

-0.15

rdr

-0.14

oeff

-0.14

//{{

-0.14

é¡ĺãģĦ

-0.14

oya

-0.13

entin

-0.13

"@"

-0.13

POSITIVE LOGITS

 Southern

0.21

 legalize

0.19

Southern

0.16

 Metal

0.15

0.14

 Country

0.14

ÙĨØ²

0.14

ãĤ¤ãĥ³ãĥĪ

0.14

 ÑģÐ»Ñĥ

0.14

 legalized

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.