INDEX

Explanations

attributes and details related to physical media products, such as books and LP records

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

woff

-0.15

bsd

-0.14

áº£ng

-0.14

Animated

-0.14

 åĳ

-0.14

chalk

-0.14

Â©Â©

-0.14

orous

-0.14

ze

-0.14

allel

-0.13

POSITIVE LOGITS

 bound

0.26

 coffee

0.25

 binding

0.24

-bound

0.22

 slip

0.22

coffee

0.22

bound

0.22

binding

0.22

 overs

0.21

Smy

0.21

Activations Density 0.085%

attributes and details related to physical media products, such as books and LP records

No Comments

No Known Activations