INDEX

Explanations

relationships and familial dynamics

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

 Couples

-0.16

Ø´ÙĪØ±

-0.14

Ð²ÐµÐ´

-0.14

 Grandma

-0.13

 Dorm

-0.13

ìĿ´ìĹĲ

-0.13

initely

-0.13

icros

-0.13

overy

-0.13

POSITIVE LOGITS

son

1.07

 sons

0.90

 daughter

0.90

Son

0.81

son

0.80

Son

0.77

 daughters

0.76

SON

0.74

.son

0.71

daughter

0.69

Activations Density 0.620%

relationships and familial dynamics

No Comments

No Known Activations