INDEX

Explanations

programming-related content, particularly focusing on command line interfaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÅĻej

-0.17

Å¡ov

-0.15

usiness

-0.14

ween

-0.14

Fir

-0.14

 Fortune

-0.14

ÐļÐ¢

-0.14

 Ð·Ð°ÑĤ

-0.13

Ã¶k

-0.13

POSITIVE LOGITS

.Option

0.23

 getopt

0.23

 Option

0.21

.help

0.21

.Help

0.21

 Help

0.21

 usage

0.21

.usage

0.20

 option

0.20

 help

0.20

Activations Density 0.021%

programming-related content, particularly focusing on command line interfaces

No Comments

No Known Activations