INDEX

Explanations

instances of the word "open" and its variations, indicating activities related to the opening of places or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

quez

-0.16

Ð¿Ð¾ÑĢ

-0.15

ÌĨ

-0.15

ucci

-0.14

ula

-0.14

ories

-0.14

lej

-0.14

ÑĥÑĩÐ°Ñģ

-0.14

ala

-0.13

uten

-0.13

POSITIVE LOGITS

/open

0.18

stein

0.17

ulares

0.16

nung

0.16

à¸Ķà¸³à¹Ģà¸Ļ

0.15

-ended

0.15

nist

0.15

maal

0.15

leaf

0.15

-source

0.15

Activations Density 0.057%

instances of the word "open" and its variations, indicating activities related to the opening of places or events

No Comments

No Known Activations