INDEX

Explanations

terms related to vacancy and unoccupied spaces

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

adle

-0.19

hell

-0.15

Rif

-0.15

oteca

-0.15

istical

-0.15

edException

-0.15

wd

-0.15

throp

-0.15

ahn

-0.14

èĩ¨

-0.14

POSITIVE LOGITS

uum

0.28

ancies

0.23

ancy

0.21

vac

0.20

vvm

0.20

 cleaner

0.20

vac

0.20

 Ð²Ð°Ðº

0.18

illation

0.18

Vac

0.18

Activations Density 0.012%

terms related to vacancy and unoccupied spaces

No Comments

No Known Activations