INDEX

Explanations

connections and interactions between different subjects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

orf

-0.20

upal

-0.17

BindingUtil

-0.16

emiz

-0.15

ixel

-0.15

isay

-0.15

ipop

-0.15

 æ·

-0.15

-INF

-0.14

 OMIT

-0.14

POSITIVE LOGITS

 nhau

0.26

 other

0.24

 others

0.23

other

0.20

others

0.17

 ones

0.16

åħ¶ä»ĸ

0.16

 another

0.16

 altre

0.15

 otras

0.15

Activations Density 0.133%

connections and interactions between different subjects or entities

No Comments

No Known Activations