INDEX

Explanations

programming-related concepts and terminology

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

ossier

-0.16

Binder

-0.14

iras

-0.14

uguay

-0.13

ê²¬

-0.13

ä¸ĭè½½æ¬¡æķ°

-0.13

ç¨¿

-0.13

addon

-0.13

olta

-0.13

orf

-0.12

POSITIVE LOGITS

bar

1.47

Bar

1.40

bar

1.39

Bar

1.36

-bar

1.31

_bar

1.22

BAR

1.21

-Bar

1.20

BAR

1.18

.bar

1.16

Activations Density 0.325%

programming-related concepts and terminology

No Comments

No Known Activations