INDEX

Explanations

concepts related to partnerships and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

inton

-0.19

anging

-0.14

å¼ı

-0.14

ennes

-0.14

à¤Ĥà¤ļ

-0.14

ÑĤÐµÑĢÐ¸

-0.14

ROP

-0.14

ssi

-0.13

mav

-0.13

POSITIVE LOGITS

 alike

0.36

 together

0.36

 Together

0.29

ä¸Ģèµ·

0.28

Together

0.25

 zusammen

0.21

 Ð²Ð¼ÐµÑģÑĤÐµ

0.20

 ÑĢÐ°Ð·Ð¾Ð¼

0.20

 equally

0.19

ä¸Ģæł·

0.18

Activations Density 0.130%

concepts related to partnerships and connections

No Comments

No Known Activations