INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

æ¢¨

-0.16

ellido

-0.16

inkel

-0.15

 Strikes

-0.14

 ãĤ¢ãĥ«

-0.14

itti

-0.14

argent

-0.13

 (“

-0.13

UGH

-0.13

anje

-0.13

POSITIVE LOGITS

ÑĻ

0.17

ipel

0.16

aha

0.16

dn

0.15

 keen

0.15

elden

0.15

},{↵

0.14

ìŀĲìĿ¸

0.14

rada

0.14

InvalidOperationException

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.