INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 verst

-0.14

irc

-0.14

Ban

-0.14

ï

-0.14

renom

-0.13

ă

-0.13

/TT

-0.13

[DllImport

-0.13

.googlecode

-0.13

ette

-0.12

POSITIVE LOGITS

argon

0.16

aleb

0.14

gov

0.13

UTION

0.13

ÐµÑĢÐµÑĩ

0.13

azz

0.13

imir

0.13

.slim

0.13

ÐĽÐĲ

0.13

ofil

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.