INDEX

Explanations

instances of the word "know" and its variations, indicating a focus on knowledge and awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

à¤µà¤¤

-0.15

quist

-0.14

Ø³Ø§Øª

-0.14

faction

-0.14

ãĥ¥

-0.13

iÃ¨res

-0.13

eward

-0.13

uman

-0.12

ipar

-0.12

anst

-0.12

POSITIVE LOGITS

 about

0.40

how

0.34

ledged

0.32

-how

0.32

 what

0.30

 enough

0.29

who

0.29

about

0.28

led

0.28

lege

0.27

Activations Density 0.113%

instances of the word "know" and its variations, indicating a focus on knowledge and awareness

No Comments

No Known Activations