INDEX

Explanations

references to clothing and dress codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

erral

-0.15

rawer

-0.15

Ð¼Ñı

-0.15

oplan

-0.15

 automatically

-0.14

blink

-0.14

 automat

-0.13

 explicitly

-0.13

 blink

-0.13

altimore

-0.13

POSITIVE LOGITS

 wearing

0.29

 dress

0.28

 outfits

0.27

 outfit

0.27

 wear

0.25

dress

0.25

 attire

0.23

 wears

0.23

 dressed

0.23

æľį

0.23

Activations Density 0.298%

references to clothing and dress codes

No Comments

No Known Activations