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

illin

-0.16

 Rowe

-0.15

ollar

-0.15

osto

-0.15

¯

-0.15

lea

-0.15

 Hull

-0.14

arl

-0.14

auled

-0.14

abra

-0.14

POSITIVE LOGITS

_LCD

0.16

0.15

deniz

0.14

uyá»ħn

0.14

fkk

0.14

\CMS

0.14

éĻ½

0.14

isters

0.14

ãĥ¥

0.14

 fitte

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.