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

uilder

-0.19

ãĥ¼ãĥĲ

-0.15

uth

-0.15

bre

-0.15

subscribe

-0.15

ghost

-0.14

isten

-0.14

orida

-0.14

 subscribe

-0.13

Inst

-0.13

POSITIVE LOGITS

NAN

0.15

han

0.15

.flat

0.14

benh

0.14

Cyr

0.14

æĬ¼

0.14

ÙĨØ´

0.14

cul

0.14

Moy

0.13

ence

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.