INDEX

Explanations

significant architectural features and cultural landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

æķ·

-0.18

NI

-0.15

seau

-0.15

ollar

-0.14

 Retorna

-0.13

 quanh

-0.13

PLICIT

-0.13

depth

-0.13

 ÏĢÎµÏģÎ¹Î¿

-0.13

POSITIVE LOGITS

 rising

0.31

 tower

0.30

 towers

0.29

 rise

0.29

 risen

0.26

rising

0.26

-rise

0.26

tower

0.25

 rises

0.25

Activations Density 0.177%

significant architectural features and cultural landmarks

No Comments

No Known Activations