INDEX

Explanations

elements related to newline characters and formatting in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

enco

-0.15

ums

-0.15

("`

-0.14

umn

-0.14

éĸ¢

-0.14

Ú¯Ø²

-0.14

ensual

-0.14

/session

-0.13

 rigor

-0.13

rogen

-0.13

POSITIVE LOGITS

shima

0.17

elize

0.15

ynch

0.15

Ä±t

0.14

Nin

0.14

.BorderFactory

0.14

fil

0.14

anner

0.14

ely

0.14

otec

0.14

Activations Density 0.013%

elements related to newline characters and formatting in a programming context

No Comments

No Known Activations