INDEX

Explanations

numerical data and coordinates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

kowski

-0.18

@brief

-0.16

CRET

-0.16

icontrol

-0.15

atest

-0.15

odÃŃ

-0.15

áº¥u

-0.15

.myapplication

-0.14

ameda

-0.14

HT

-0.14

POSITIVE LOGITS

Â°

0.36

 degrees

0.31

 degree

0.30

åº¦

0.27

 Â°

0.26

 Degree

0.25

degree

0.24

Â°N

0.24

deg

0.23

-degree

0.23

Activations Density 0.010%

numerical data and coordinates

No Comments

No Known Activations