INDEX

Explanations

conditional phrases that indicate uncertainty or dependency on specific circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

frey

-0.18

quette

-0.15

kola

-0.15

kul

-0.14

iye

-0.14

zburg

-0.14

 Fleet

-0.14

ntity

-0.14

POSITIVE LOGITS

 your

0.32

you

0.30

ä½ł

0.27

ä½łçļĦ

0.26

 youre

0.24

 YOUR

0.22

your

0.22

 báº¡n

0.22

 à¤Ĩà¤ªà¤ķ

0.21

you

0.21

Activations Density 0.192%

conditional phrases that indicate uncertainty or dependency on specific circumstances

No Comments

No Known Activations