INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

.appspot

-0.16

appings

-0.15

akit

-0.14

 Gazette

-0.14

pone

-0.14

Woo

-0.14

Lif

-0.14

 Madden

-0.14

 Works

-0.13

POSITIVE LOGITS

ngle

0.19

itial

0.17

arth

0.15

 doctr

0.15

rb

0.14

 Strom

0.14

underscore

0.14

ç·Ĵ

0.14

ril

0.14

thr

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.