INDEX

Explanations

references to the name "Zoe" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ARGIN

-0.15

istr

-0.15

iod

-0.14

ip

-0.14

ector

-0.14

zones

-0.14

ÑģÑĤÐ²ÐµÐ½Ð½ÑĭÐ¹

-0.14

è³ª

-0.14

ipc

-0.14

agner

-0.13

POSITIVE LOGITS

unft

0.20

ppelin

0.18

=z

0.17

ebra

0.17

abbix

0.17

pered

0.17

ephir

0.16

ucchini

0.16

geist

0.16

/Z

0.16

Activations Density 0.077%

references to the name "Zoe" and related variations

No Comments

No Known Activations