INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

here

-0.16

 pride

-0.15

ushing

-0.14

via

-0.14

oni

-0.14

oproject

-0.14

orp

-0.14

ine

-0.14

POSITIVE LOGITS

 having

0.24

 being

0.21

how

0.20

 hearing

0.18

having

0.18

 seeing

0.18

Having

0.18

 cÃ³mo

0.17

 heck

0.17

 Having

0.17

Activations Density 0.062%

expressions of gratitude and appreciation

No Comments

No Known Activations