INDEX

Explanations

the concept of "best" or optimal choices in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

lasses

-0.19

ersen

-0.18

 gore

-0.15

 McGr

-0.15

 economical

-0.15

avorite

-0.14

kest

-0.14

stry

-0.14

orest

-0.14

tere

-0.14

POSITIVE LOGITS

eh

0.20

ell

0.18

ebin

0.17

ellt

0.17

emp

0.17

 æº

0.17

eb

0.17

ehen

0.17

anden

0.17

Ã¼nde

0.17

Activations Density 0.009%

the concept of "best" or optimal choices in various contexts

No Comments

No Known Activations