INDEX

Explanations

mentions of personal experiences and family interactions

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

 mÃ¬nh

-0.26

 oneself

-0.20

 yourself

-0.18

 yourselves

-0.17

 Yourself

-0.16

we

-0.14

 theirs

-0.14

We

-0.13

jeg

-0.13

We

-0.13

POSITIVE LOGITS

my

1.12

æĪĳçļĦ

0.91

my

0.84

 mijn

0.76

=my

0.72

(my

0.71

my

0.70

.my

0.69

_my

0.69

meu

0.69

Activations Density 1.078%

mentions of personal experiences and family interactions

No Comments

No Known Activations