INDEX

Explanations

references to emotional manipulation and accountability in relationships

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

sed

-0.20

amba

-0.19

ston

-0.19

 Ston

-0.19

Sed

-0.17

-0.16

 sust

-0.15

 Wagner

-0.15

ijo

-0.15

eldon

-0.15

POSITIVE LOGITS

 Sarah

1.11

sar

1.00

Sarah

0.99

SAR

0.92

Sar

0.85

sar

0.76

 Sara

0.67

 Saras

0.51

 Sanders

0.50

 Darwin

0.50

Activations Density 0.124%

references to emotional manipulation and accountability in relationships

No Comments

No Known Activations