INDEX

Explanations

programming-related syntax in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 trÃº

-0.16

trak

-0.14

Ø¯Ø§

-0.14

asio

-0.13

ÑıÑģ

-0.13

«ĺ

-0.13

stalk

-0.13

OLEAN

-0.13

(éĩĳ

-0.13

vik

-0.13

POSITIVE LOGITS

Ð»Ð¸ÑĤ

0.18

riba

0.16

0.15

afil

0.14

grav

0.14

ces

0.14

 Stevens

0.14

Ð¸ÑĩÐ°

0.14

oucÃŃ

0.14

0.13

Activations Density 0.007%

programming-related syntax in code

No Comments

No Known Activations