INDEX

Explanations

concepts related to regulations and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

erten

-0.17

.scalablytyped

-0.16

 themselves

-0.15

ulg

-0.15

 Hemp

-0.14

asal

-0.14

argest

-0.14

laus

-0.14

efon

-0.14

erte

-0.13

POSITIVE LOGITS

 exists

0.43

 existed

0.32

 exist

0.31

exists

0.29

 accompanies

0.28

was

0.27

 existe

0.26

 Exist

0.26

 Exists

0.25

is

0.25

Activations Density 0.466%

concepts related to regulations and governance

No Comments

No Known Activations