INDEX

Explanations

programming-related syntax and structures within code

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

avl

-0.18

Unmarshaller

-0.17

ocz

-0.17

-dat

-0.16

aisal

-0.16

awe

-0.15

ofire

-0.15

ouv

-0.14

-addons

-0.14

.DefaultCellStyle

-0.14

POSITIVE LOGITS

Sk

0.38

sk

0.32

Sk

0.29

SK

0.26

-sk

0.26

sk

0.25

.sk

0.24

(sk

0.24

SK

0.22

_DEFINED

0.20

Activations Density 0.001%

programming-related syntax and structures within code

No Comments

No Known Activations