INDEX

Explanations

questions that inquire about methods, processes, or approaches to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 GOODMAN

-0.19

uled

-0.16

 filmpjes

-0.15

uisse

-0.15

omaly

-0.15

ickerView

-0.14

Ð´Ð°Ñı

-0.14

orsi

-0.14

anship

-0.14

ingleton

-0.14

POSITIVE LOGITS

 seemingly

0.20

 best

0.20

/if

0.18

 various

0.18

 changes

0.17

 technology

0.17

 being

0.17

 exposure

0.17

 else

0.16

 everyday

0.16

Activations Density 0.064%

questions that inquire about methods, processes, or approaches to various topics

No Comments

No Known Activations