INDEX

Explanations

programming-related terms and functions

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

Åº

-0.20

athan

-0.18

Ð²Ð¾Ð´

-0.16

achuset

-0.15

.SDK

-0.15

ëıħ

-0.15

olley

-0.15

airo

-0.14

 Trades

-0.14

arters

-0.14

POSITIVE LOGITS

.twig

0.17

($__

0.17

 twig

0.16

imler

0.15

 Twig

0.15

dÃŃ

0.15

 RequestContext

0.15

krit

0.14

 Swift

0.14

Arena

0.14

Activations Density 0.006%

programming-related terms and functions

No Comments

No Known Activations