INDEX

Explanations

references to financial profits or gains

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

igital

-0.17

ikat

-0.15

gg

-0.15

 reife

-0.14

DAQ

-0.14

EMPTY

-0.14

pak

-0.13

uring

-0.13

Ã¤tt

-0.13

nam

-0.13

POSITIVE LOGITS

ZO

0.15

 component

0.15

coholic

0.15

/Branch

0.15

isible

0.14

ysa

0.14

dub

0.14

 topl

0.13

 Transition

0.13

Activations Density 0.178%

references to financial profits or gains

No Comments

No Known Activations