INDEX

Explanations

references to smoking and related behaviors

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

 Washer

-0.16

Ã¶z

-0.15

iÃª

-0.14

|#

-0.14

 æ¢

-0.14

gem

-0.14

ibir

-0.14

 Oman

-0.14

utr

-0.14

andex

-0.13

POSITIVE LOGITS

 tobacco

0.73

 smoking

0.72

 cigarette

0.67

 smokers

0.65

 cigarettes

0.65

 smoker

0.64

 Tobacco

0.64

 Smoking

0.64

 smoke

0.63

 nicotine

0.60

Activations Density 0.155%

references to smoking and related behaviors

No Comments

No Known Activations