INDEX

Explanations

phrases related to quality and satisfaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Zuk

-0.19

opoulos

-0.16

alon

-0.16

mans

-0.15

fly

-0.15

apers

-0.15

rec

-0.15

iah

-0.14

owitz

-0.14

aver

-0.14

POSITIVE LOGITS

uais

0.17

ESA

0.16

ãĥªãĥ¼ãĤº

0.15

idar

0.15

variants

0.15

å½©

0.15

 ÑĤÐ¸

0.15

IMO

0.15

0.14

à¸Ļà¸Ķ

0.14

Activations Density 0.375%

phrases related to quality and satisfaction

No Comments

No Known Activations