INDEX

Explanations

phrases indicating possibility or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 presumably

-0.30

 probably

-0.29

 apparently

-0.27

probably

-0.25

 Probably

-0.24

 undoubtedly

-0.24

 reportedly

-0.23

 surely

-0.23

 evidently

-0.23

 zÅĻejmÄĽ

-0.22

POSITIVE LOGITS

 someday

0.26

 even

0.23

 slightly

0.20

TOO

0.19

/pro

0.19

 better

0.19

 sogar

0.18

 some

0.18

 best

0.17

too

0.17

Activations Density 0.230%

phrases indicating possibility or uncertainty

No Comments

No Known Activations