INDEX

Explanations

concepts and terminology related to academic and professional fields, especially in relation to psychology and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

rint

-0.21

stantiate

-0.15

cco

-0.14

 opat

-0.14

SEG

-0.14

ä»¥åıĬ

-0.13

asin

-0.13

áº«n

-0.13

Ã¡cil

-0.13

à¸²à¸Ķ

-0.13

POSITIVE LOGITS

 refers

0.54

 refer

0.48

 referring

0.43

refer

0.36

 Refer

0.32

 referred

0.30

ãģ¨ãģ¯

0.29

 refere

0.29

Refer

0.29

 describes

0.28

Activations Density 0.306%

concepts and terminology related to academic and professional fields, especially in relation to psychology and decision-making processes

No Comments

No Known Activations