INDEX

Explanations

elements related to support and success 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ìĿ´ê³ł

-0.21

 totiÅ¾

-0.20

)&&

-0.20

)&&(

-0.20

 however

-0.18

 ìŀĪê³ł

-0.17

'&&

-0.15

ãģ§ãģĤãĤĬ

-0.15

however

-0.15

 zwar

-0.15

POSITIVE LOGITS

 accordingly

0.31

 consequently

0.20

 therein

0.19

 serta

0.17

 ther

0.17

 thereof

0.14

yat

0.14

 Ø¢ÙĨ

0.14

noch

0.14

 Consequently

0.14

Activations Density 0.913%

elements related to support and success in various contexts

No Comments

No Known Activations