INDEX

Explanations

rhetorical questions and expressions of insight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 addCriterion

-0.17

/apis

-0.17

ç¹

-0.15

¢åįķ

-0.15

ngÃ¶r

-0.15

hya

-0.14

znik

-0.14

kre

-0.14

rijk

-0.14

 Annex

-0.14

POSITIVE LOGITS

 totiÅ¾

0.31

Nam

0.22

Nam

0.20

 ëķĮë¬¸

0.20

nam

0.20

 because

0.19

 nÃ¤

0.18

 indeed

0.18

yes

0.18

nam

0.17

Activations Density 0.180%

rhetorical questions and expressions of insight

No Comments

No Known Activations

rhetorical questions and expressions of insight

No Comments

No Known Activations