INDEX

Explanations

phrases and conjunctions used to connect ideas and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

boy

-0.14

BindingUtil

-0.13

_AUX

-0.13

Å

-0.13

elf

-0.13

vet

-0.13

\s

-0.13

 ÑģÐºÐ»Ð°Ð´Ñĸ

-0.13

 âĵĺ

-0.12

POSITIVE LOGITS

 others

0.42

others

0.28

/or

0.28

 Others

0.27

etc

0.23

 other

0.21

ients

0.21

Others

0.21

phans

0.19

 countless

0.19

Activations Density 0.206%

phrases and conjunctions used to connect ideas and concepts

No Comments

No Known Activations