INDEX

Explanations

programming constructs and their associated functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Lines

-0.17

 Rows

-0.15

Rol

-0.15

ÐµÑĤÐ¸Ñĩ

-0.14

 Trees

-0.14

ourt

-0.14

 Levels

-0.14

Ra

-0.14

 Stones

-0.14

Def

-0.13

POSITIVE LOGITS

unc

0.15

odzi

0.14

 incom

0.14

elf

0.13

com

0.13

unc

0.13

arga

0.13

spl

0.13

.constructor

0.13

unf

0.13

Activations Density 0.048%

programming constructs and their associated functionalities

No Comments

No Known Activations