INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

‘

-0.15

–

-0.15

ÏĢÎ¿Ïį

-0.14

 Arbitrary

-0.14

 âĢº

-0.14

-</

-0.14

eva

-0.14

utorials

-0.14

itunes

-0.14

utorial

-0.13

POSITIVE LOGITS

(((

0.25

Jew

0.24

msm

0.21

jew

0.20

=https

0.20

_https

0.19

 https

0.19

https

0.17

etc

0.17

 cuck

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.