INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

otts

-0.15

 Rodney

-0.15

Ð¾Ð»Ð°

-0.14

 tand

-0.14

ickt

-0.14

anga

-0.13

jog

-0.13

 Witness

-0.13

 illeg

-0.13

 League

-0.13

POSITIVE LOGITS

avit

0.15

elen

0.15

Å¡etÅĻ

0.14

riday

0.14

reen

0.14

cntl

0.14

acket

0.14

fun

0.13

sho

0.13

avra

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.