INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ¦ãĤ©

-0.15

ields

-0.14

zug

-0.14

åĬĩ

-0.14

ufs

-0.14

onas

-0.13

Ú©Ø´

-0.13

alsa

-0.13

dsn

-0.13

Ø§Ø¬Ø±

-0.13

POSITIVE LOGITS

ilk

0.19

 earliest

0.15

Mos

0.15

ibr

0.14

 early

0.14

uti

0.14

oppel

0.14

gements

0.14

Mos

0.14

dp

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.