INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 ãĤ¢ãĤ¤

-0.15

itsu

-0.15

leo

-0.14

abela

-0.14

ÐµÐ¶

-0.14

ãĥģãĥ¥

-0.14

 Benn

-0.13

 tune

-0.13

ma

-0.13

ref

-0.13

POSITIVE LOGITS

UIBarButtonItem

0.15

.scalablytyped

0.14

 fucking

0.14

aight

0.14

Łèĥ½

0.14

erro

0.14

peon

0.14

Unauthorized

0.14

Selectors

0.13

heimer

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.