INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

imd

-0.19

datagrid

-0.15

assen

-0.14

Ð¾Ð»Ð¾Ð¼

-0.14

 disap

-0.14

uess

-0.14

 Gins

-0.14

Ð¾ÑĤÑĮ

-0.14

eless

-0.14

emin

-0.14

POSITIVE LOGITS

VERR

0.16

 Gors

0.16

rel

0.15

 rehab

0.15

 tane

0.15

 Mand

0.14

illard

0.14

stuff

0.14

imit

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.