INDEX

Explanations

phrases indicating necessity or requirement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

reen

-0.16

utex

-0.15

assis

-0.14

ASIC

-0.14

 Commerce

-0.14

otion

-0.14

Twig

-0.14

unker

-0.14

 elast

-0.14

ntag

-0.14

POSITIVE LOGITS

 anymore

0.23

 worry

0.20

 fret

0.19

 worrying

0.16

 necessarily

0.16

lessly

0.15

iere

0.14

ieri

0.14

 Gates

0.14

*&

0.14

Activations Density 0.092%

phrases indicating necessity or requirement

No Comments

No Known Activations