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

atch

-0.14

subclass

-0.14

hpp

-0.14

outputs

-0.14

oho

-0.14

im

-0.14

apk

-0.13

æĶ

-0.13

oret

-0.13

_epi

-0.13

POSITIVE LOGITS

 Ð´ÐµÐ»Ð¾

0.16

 especially

0.16

 Telephone

0.15

ifax

0.14

especially

0.14

ãĥ§

0.13

 ì²ł

0.13

 extents

0.13

inaire

0.13

ÑĢÑĥÐº

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.