INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

isay

-0.17

ych

-0.15

INLINE

-0.15

orgia

-0.15

 Ø§ÙĦØµÙĨ

-0.14

 é¤

-0.14

alim

-0.14

ardon

-0.14

phis

-0.14

phin

-0.14

POSITIVE LOGITS

 alike

0.28

izo

0.16

ulent

0.16

epy

0.15

paste

0.14

å®ħ

0.14

epam

0.14

ep

0.14

 Mask

0.13

agged

0.13

Activations Density 0.101%

No Comments

No Known Activations