INDEX

Explanations

references to causes and effects of death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-BEGIN

-0.14

Disallow

-0.14

alace

-0.14

ÑģÑĮÐºÐ¾

-0.13

ÑģÐ¸ÑĤ

-0.13

inium

-0.13

cko

-0.13

aylight

-0.13

æģ¶

-0.13

(æľĪ

-0.13

POSITIVE LOGITS

 death

0.98

 deaths

0.89

 died

0.84

death

0.79

 dying

0.75

æŃ»

0.75

 Death

0.74

 dies

0.73

 dead

0.73

æŃ»äº¡

0.73

Activations Density 1.137%

references to causes and effects of death

No Comments

No Known Activations