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

 -↵↵

-0.16

'[

-0.15

eza

-0.15

idor

-0.15

 neighbouring

-0.15

quer

-0.14

itr

-0.14

hti

-0.14

nelly

-0.14

POSITIVE LOGITS

brtc

0.17

isci

0.17

0.15

ekli

0.15

 Iron

0.15

ICENSE

0.15

buie

0.15

Narr

0.14

avic

0.14

Mo

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.