INDEX

Explanations

the word "Variation" or its variants, indicating a focus on diversity or differences

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

ilt

-0.20

ining

-0.17

ilit

-0.17

ra

-0.16

RACT

-0.16

med

-0.15

ematik

-0.15

ri

-0.15

Ø¯

-0.15

mes

-0.15

POSITIVE LOGITS

0.25

ETY

0.22

eties

0.21

uos

0.21

ety

0.21

etÃł

0.20

ums

0.20

Ã©tÃ©

0.19

juan

0.19

amente

0.18

Activations Density 0.045%

the word "Variation" or its variants, indicating a focus on diversity or differences

No Comments

No Known Activations