INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.da

-0.16

egrate

-0.15

Ã©mon

-0.15

hes

-0.14

ÅĻad

-0.14

.tk

-0.14

 Late

-0.14

euillez

-0.13

vit

-0.13

entine

-0.13

POSITIVE LOGITS

 Guard

0.17

Oro

0.15

al

0.15

isko

0.14

ipro

0.14

enburg

0.14

ark

0.14

informatics

0.13

/local

0.13

Guard

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.