INDEX

Explanations

phrases related to 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ø§Ù

-0.18

ilt

-0.16

illac

-0.16

ux

-0.15

hana

-0.15

arth

-0.15

inar

-0.14

oglob

-0.14

 BÄĽ

-0.14

SKI

-0.13

POSITIVE LOGITS

azer

0.16

è°±

0.15

reta

0.15

 Bout

0.15

AndPassword

0.14

ajes

0.14

azaar

0.14

Ø³ÙĪØ¨

0.14

ãĥ¼ãĥ³

0.13

ì±Ħ

0.13

Activations Density 0.026%

phrases related to possession or ownership

No Comments

No Known Activations