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

ekil

-0.15

aws

-0.15

iglia

-0.14

å¤®

-0.14

/commons

-0.14

Å¡ek

-0.13

lider

-0.13

ä¼¯

-0.13

 proh

-0.13

Ã©ry

-0.13

POSITIVE LOGITS

0.15

 everybody

0.14

 anybody

0.13

utherland

0.13

Î¸ÎŃ

0.13

 trab

0.13

åĶ®

0.13

Ø§Ù

0.13

riba

0.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.