INDEX

Explanations

bibliographic information and references related to books and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.18

 shoulder

-0.15

 otherwise

-0.15

isse

-0.15

 liberal

-0.14

leg

-0.14

ialis

-0.14

NB

-0.14

then

-0.14

 Magazine

-0.14

POSITIVE LOGITS

glich

0.17

juan

0.15

/bower

0.15

kenin

0.14

.VideoCapture

0.14

LOUR

0.14

ISM

0.13

.toHexString

0.13

DidLoad

0.13

 Angiospermae

0.13

Activations Density 0.004%

bibliographic information and references related to books and publications

No Comments

No Known Activations