INDEX

Explanations

programming-related markup and code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

çµĲ

-0.15

ered

-0.15

orgia

-0.14

.IContainer

-0.14

ä¸Ńãģ«

-0.13

ahren

-0.13

 Merrill

-0.13

IRE

-0.13

riages

-0.13

ABCDEFGHI

-0.13

POSITIVE LOGITS

///

0.23

///

0.19

 Â·

0.17

Â·

0.17

imeline

0.16

 Bates

0.16

 ///↵

0.15

 pestic

0.15

.Dimension

0.15

##

0.14

Activations Density 0.011%

programming-related markup and code structure

No Comments

No Known Activations