INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oa

-0.16

ainter

-0.15

 lick

-0.14

ora

-0.14

 freezer

-0.14

owski

-0.13

ippy

-0.13

à¸¸à¸ª

-0.13

 pioneers

-0.13

loquent

-0.13

POSITIVE LOGITS

utr

0.18

 income

0.15

ativity

0.15

.tax

0.15

 Income

0.15

idUser

0.15

Income

0.14

ìħĶ

0.14

.misc

0.14

Ã³r

0.14

Activations Density 0.095%

No Comments

No Known Activations