INDEX

Explanations

phrases related to programming languages and tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

fu

-0.18

iffe

-0.17

Ha

-0.16

Vu

-0.16

Ha

-0.15

ha

-0.15

udi

-0.14

iglia

-0.14

uyla

-0.14

ÑĸÑĶ

-0.14

POSITIVE LOGITS

cono

0.25

 possono

0.25

 sono

0.25

 teng

0.25

anno

0.25

pong

0.24

ano

0.23

 pong

0.23

 hanno

0.22

ono

0.21

Activations Density 0.003%

phrases related to programming languages and tools

No Comments

No Known Activations