INDEX

Explanations

programming-related syntax and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

anner

-0.16

 Ø§ÙĦÙĪØµ

-0.14

adiens

-0.14

 Hurt

-0.14

Unsigned

-0.14

ÏģÎ¿ÏĤ

-0.14

abstractmethod

-0.13

athlon

-0.13

ç¦

-0.13

POSITIVE LOGITS

 auto

0.34

auto

0.29

/auto

0.26

.emplace

0.25

.auto

0.24

(auto

0.24

 constexpr

0.24

	auto

0.23

-auto

0.22

 noexcept

0.20

Activations Density 0.062%

programming-related syntax and constructs

No Comments

No Known Activations