INDEX

Explanations

references to before-and-after weight loss imagery and motivation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

uxtap

-0.15

illin

-0.15

ÑĢÑİ

-0.15

PIO

-0.14

readcr

-0.14

Ð½Ð°Ð´Ð»ÐµÐ¶

-0.14

inka

-0.13

UMB

-0.13

iliz

-0.13

å¹´ä»£

-0.13

POSITIVE LOGITS

 weigh

0.30

 accountability

0.27

 Accountability

0.26

 Weight

0.24

 weight

0.24

weigh

0.23

 weighing

0.23

 portion

0.21

Weight

0.21

 weighs

0.21

Activations Density 0.035%

references to before-and-after weight loss imagery and motivation

No Comments

No Known Activations