INDEX

Explanations

output statements in various programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

od

-0.17

 quote

-0.17

fro

-0.16

 Industry

-0.16

od

-0.16

 Quote

-0.15

 quotation

-0.15

 industry

-0.14

fur

-0.14

ategorie

-0.14

POSITIVE LOGITS

("================

0.18

("\

0.18

StrLn

0.17

.writeln

0.17

.println

0.16

("\

0.16

erdem

0.16

_hi

0.16

Ã¡bado

0.15

('\

0.15

Activations Density 0.032%

output statements in various programming languages

No Comments

No Known Activations