INDEX

Explanations

phrases related to separation or escaping

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

onta

-0.17

lech

-0.15

UNE

-0.14

bah

-0.14

Ø§ÙħØ§

-0.14

 heter

-0.14

à¸Ńà¹Ģà¸£

-0.14

irth

-0.14

non

-0.14

POSITIVE LOGITS

è±¡

0.17

á»£

0.16

ÑĪÐºÐ°

0.15

ody

0.15

 Writers

0.15

issant

0.14

ajar

0.14

wie

0.14

ÐµÐ³Ð¾ÑĢ

0.14

arning

0.14

Activations Density 0.031%

phrases related to separation or escaping

No Comments

No Known Activations