INDEX

Explanations

phrases indicating ownership or associative relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

jay

-0.15

ouch

-0.14

oss

-0.14

orne

-0.14

rig

-0.14

.Css

-0.13

antal

-0.13

fu

-0.13

á»Ĩ

-0.13

ampler

-0.13

POSITIVE LOGITS

 sorts

0.23

-course

0.19

sted

0.19

course

0.17

-pocket

0.16

venes

0.16

 course

0.16

entimes

0.15

tt

0.15

à¤¼

0.15

Activations Density 0.499%

phrases indicating ownership or associative relationships

No Comments

No Known Activations