INDEX

Explanations

programming syntax, particularly related to object-oriented and functional aspects of code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.17

resa

-0.17

ãĤĤãģªãģĦ

-0.16

rie

-0.15

ario

-0.15

con

-0.15

con

-0.14

Ã§on

-0.14

ipping

-0.14

POSITIVE LOGITS

SCRI

0.15

.weixin

0.15

owie

0.15

Ø§Ø¨ÙĤ

0.15

_tF

0.15

Streamer

0.15

pus

0.15

 pushViewController

0.15

ltk

0.14

cmc

0.14

Activations Density 0.072%

programming syntax, particularly related to object-oriented and functional aspects of code

No Comments

No Known Activations