INDEX

Explanations

phrases indicating updates or new releases of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

.BLL

-0.15

 repeatedly

-0.14

 Ð·Ð°Ðº

-0.14

apiro

-0.13

enberg

-0.13

usty

-0.13

èĦ±

-0.13

hor

-0.13

 Jays

-0.13

 ÙģØ±ÙĪØ¯Ú¯Ø§Ùĩ

-0.13

POSITIVE LOGITS

rens

0.16

PEnd

0.15

IPH

0.15

asz

0.15

vÄĽt

0.14

-lfs

0.14

xFFF

0.14

andin

0.14

 newest

0.14

ARGIN

0.14

Activations Density 0.029%

phrases indicating updates or new releases of information

No Comments

No Known Activations