INDEX

Explanations

expressions of love and appreciation towards various subjects, particularly in cinema and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ã¢u

-0.15

iants

-0.15

Åº

-0.14

 consequences

-0.14

rif

-0.14

 KÃ¼r

-0.14

RR

-0.13

 vrij

-0.13

urch

-0.13

 virgin

-0.13

POSITIVE LOGITS

why

0.35

 reasons

0.32

why

0.29

Why

0.28

Why

0.28

 reason

0.27

 Reasons

0.27

WHY

0.24

_reason

0.23

reason

0.23

Activations Density 0.141%

expressions of love and appreciation towards various subjects, particularly in cinema and entertainment

No Comments

No Known Activations