INDEX

Explanations

references to items, elements, or instances that are specified as the first, last, or best in the context of a list or collection

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

dir

-0.14

 sides

-0.14

beck

-0.14

 acompan

-0.14

ÐºÐµÑĤ

-0.14

affer

-0.14

apsed

-0.14

-0.13

tbl

-0.13

POSITIVE LOGITS

 amongst

0.17

/latest

0.17

 ÑģÑĢÐµÐ´Ð¸

0.17

OrDefault

0.17

among

0.16

ãĥŃãĥ³

0.16

 among

0.16

ãĥ©ãĤ¹

0.15

fur

0.14

available

0.14

Activations Density 0.120%

references to items, elements, or instances that are specified as the first, last, or best in the context of a list or collection

No Comments

No Known Activations