INDEX

Explanations

phrases related to self-presentation 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ucz

-0.16

 Roof

-0.14

ometown

-0.14

 Sofa

-0.13

 gums

-0.13

 HANDLE

-0.13

 roofs

-0.13

 stabilized

-0.12

ÑĢÐµÐ±

-0.12

 roof

-0.12

POSITIVE LOGITS

 clothing

0.52

 dress

0.50

 clothes

0.49

 dressing

0.49

 fashion

0.48

 wardrobe

0.47

 Dress

0.46

 Clothing

0.45

 Fashion

0.42

 dresses

0.42

Activations Density 0.442%

phrases related to self-presentation and dress codes

No Comments

No Known Activations