INDEX

Explanations

instances of expressing gratitude or appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

loor

-0.16

estation

-0.15

uby

-0.14

à¸±à¸Ĺ

-0.14

erva

-0.14

 ties

-0.14

ork

-0.13

nev

-0.13

AD

-0.13

POSITIVE LOGITS

Å¾el

0.16

0.15

ulan

0.15

AFC

0.14

asi

0.14

 Claw

0.13

ledi

0.13

elsey

0.13

precated

0.13

Activations Density 0.000%

instances of expressing gratitude or appreciation

No Comments

No Known Activations