INDEX

Explanations

elements related to system calls and programming constructs 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

hoa

-0.17

 PROGMEM

-0.16

 Lambert

-0.16

jis

-0.15

nim

-0.15

åĢĴ

-0.15

ega

-0.15

.yy

-0.14

 Ð¿Ð»

-0.14

acades

-0.14

POSITIVE LOGITS

Fd

0.20

FD

0.20

FD

0.20

semb

0.20

 fork

0.19

fd

0.18

 Binder

0.17

fd

0.17

endir

0.17

fds

0.17

Activations Density 0.075%

elements related to system calls and programming constructs in code

No Comments

No Known Activations