INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

acos

-0.16

rial

-0.15

ENA

-0.15

andan

-0.15

 ÎļÏĮ

-0.14

gra

-0.14

izr

-0.14

oproject

-0.14

ROLS

-0.13

PEND

-0.13

POSITIVE LOGITS

gni

0.15

æ±Ĺ

0.15

 hears

0.14

getter

0.14

 Taylor

0.14

 iddi

0.14

bidden

0.14

ToEnd

0.14

Taylor

0.13

utto

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.