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

tuk

-0.16

ech

-0.15

erna

-0.15

emble

-0.15

ÄĻk

-0.15

idis

-0.14

eva

-0.14

ev

-0.14

zung

-0.14

adu

-0.14

POSITIVE LOGITS

awks

0.20

olics

0.19

lsen

0.18

awk

0.18

lsru

0.17

mega

0.17

Ì£

0.17

snap

0.16

ammed

0.16

Activations Density 0.015%

No Comments

No Known Activations