INDEX

Explanations

structures indicating the presence of code blocks or objects in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ija

-0.17

owie

-0.16

RIPTION

-0.16

rans

-0.15

åĲ¹

-0.15

-0.14

omi

-0.14

RowCount

-0.14

pression

-0.14

cott

-0.14

POSITIVE LOGITS

asic

0.15

Ð¸Ð¶

0.15

idl

0.14

least

0.14

worm

0.14

 construct

0.14

camel

0.14

 prism

0.14

gu

0.14

Sok

0.14

Activations Density 0.001%

structures indicating the presence of code blocks or objects in programming

No Comments

No Known Activations