INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

olon

-0.16

velle

-0.16

ewe

-0.15

_MEDIUM

-0.15

HttpException

-0.14

ãĥ¼ãĥĵ

-0.14

amazon

-0.14

asia

-0.14

ear

-0.13

 seal

-0.13

POSITIVE LOGITS

.com

0.24

aper

0.17

://

0.16

etta

0.16

 Bail

0.15

ripper

0.15

.ibm

0.15

TypeDef

0.14

agit

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.