INDEX

Explanations

numerical values and references to currency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ï¸ı

-0.27

sian

-0.18

-0.17

-Ñħ

-0.17

rd

-0.17

nd

-0.16

âĢ³

-0.16

-Compatible

-0.16

ledo

-0.15

ForObject

-0.15

POSITIVE LOGITS

fold

0.40

teenth

0.31

eenth

0.30

/th

0.29

iÃ¨me

0.28

/t

0.25

-four

0.24

acity

0.24

-six

0.24

-five

0.23

Activations Density 0.278%

numerical values and references to currency

No Comments

No Known Activations