INDEX

Explanations

phrases indicating possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.15

[sizeof

-0.14

 todd

-0.14

Zem

-0.14

.RightToLeft

-0.14

esktop

-0.14

 Slater

-0.14

bek

-0.13

 herr

-0.13

ÑīÐ¸Ð¼

-0.13

POSITIVE LOGITS

ulla

0.19

atti

0.16

entials

0.16

immel

0.16

ophage

0.15

udden

0.15

	throws

0.14

 again

0.13

cap

0.13

awah

0.13

Activations Density 0.196%

phrases indicating possession or ownership

No Comments

No Known Activations