INDEX

Explanations

programming-related commands and function definitions

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

izard

-0.17

 latter

-0.17

ABCDEFGHIJKLMNOP

-0.16

 later

-0.15

olib

-0.15

 Ricardo

-0.15

 THAT

-0.15

arges

-0.14

ocking

-0.14

gee

-0.14

POSITIVE LOGITS

 alors

0.31

 ÑĤÐ¾Ð³Ð´Ð°

0.30

hen

0.26

 dÃ¥

0.25

åĪĻ

0.25

then

0.25

 thÃ¬

0.25

 ÑĤÐ¾Ð´Ñĸ

0.24

 entonces

0.24

åīĩ

0.24

Activations Density 0.036%

programming-related commands and function definitions

No Comments

No Known Activations