INDEX

Explanations

numerical data and scoring related 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ð°Ð¼Ð¿

-0.15

iban

-0.15

Vict

-0.15

Otherwise

-0.14

CKER

-0.14

IGNAL

-0.13

annabin

-0.13

 otherwise

-0.13

meld

-0.13

auen

-0.13

POSITIVE LOGITS

uras

0.17

Blo

0.16

å£

0.15

 baru

0.14

 Hind

0.14

_inode

0.14

alat

0.14

sey

0.13

 Townsend

0.13

ython

0.13

Activations Density 0.008%

numerical data and scoring related to various topics

No Comments

No Known Activations