INDEX

Explanations

phrases related to beginnings or initiations

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

asures

-0.17

oline

-0.17

sey

-0.16

rung

-0.16

igue

-0.15

omik

-0.15

ISE

-0.15

ola

-0.15

annes

-0.15

oure

-0.14

POSITIVE LOGITS

swith

0.25

/end

0.23

le

0.21

bucks

0.21

utory

0.20

tÄ±r

0.20

ecz

0.20

seite

0.19

nings

0.19

-up

0.19

Activations Density 0.094%

phrases related to beginnings or initiations

No Comments

No Known Activations