INDEX

Explanations

phrases indicating support and assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

orama

-0.15

owie

-0.14

ÙĪÙī

-0.14

juan

-0.13

ROID

-0.13

ERRY

-0.13

lavÃŃ

-0.13

æ³¨

-0.13

 Loving

-0.13

Ã¢y

-0.13

POSITIVE LOGITS

 whenever

0.21

 anytime

0.20

 ìĸ¸ìłľ

0.20

 accessibility

0.19

 reachable

0.17

 ears

0.17

 Ð´Ð¾ÑģÑĤÑĥÐ¿

0.17

 accessible

0.17

 Whenever

0.17

 contact

0.16

Activations Density 0.159%

phrases indicating support and assistance

No Comments

No Known Activations