INDEX

Explanations

mathematical definitions and formulations involving probability distributions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

mani

-0.19

imet

-0.17

dek

-0.16

Longrightarrow

-0.15

jing

-0.15

echa

-0.14

meer

-0.14

lesc

-0.14

ãĥ¼ãĥķ

-0.14

ukkit

-0.14

POSITIVE LOGITS

den

0.27

stands

0.26

 stands

0.25

 stand

0.25

 denotes

0.24

 stood

0.23

DEN

0.22

Den

0.22

 refer

0.21

Den

0.21

Activations Density 0.090%

mathematical definitions and formulations involving probability distributions

No Comments

No Known Activations