INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

rej

-0.16

RVA

-0.16

 thereby

-0.16

åŁĭ

-0.15

 leveling

-0.15

iqueta

-0.15

 WINAPI

-0.14

abl

-0.14

ÑŁ

-0.14

$($

-0.14

POSITIVE LOGITS

 Mercer

0.15

odd

0.15

ijn

0.14

 Arthur

0.14

udden

0.14

Baz

0.14

iae

0.13

Phy

0.13

appa

0.13

Ð»ÑĥÑĩ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.