INDEX

Explanations

references to the concept of "once" as a temporal marker indicating a past state or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 soon

-0.23

 currently

-0.23

çĽ®åīį

-0.22

soon

-0.20

currently

-0.20

now

-0.19

 finally

-0.18

 presently

-0.17

æľĢçµĤ

-0.16

 ÑĤÐµÐ¿ÐµÑĢÑĮ

-0.16

POSITIVE LOGITS

 merely

0.29

 simply

0.28

 solely

0.24

 simplement

0.22

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.21

 only

0.20

 exclusively

0.20

(before

0.20

 thought

0.19

 ONLY

0.19

Activations Density 0.268%

references to the concept of "once" as a temporal marker indicating a past state or condition

No Comments

No Known Activations