INDEX

Explanations

phrases related to software licensing and terms of use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

querque

-0.17

KANJI

-0.16

ï»¿#

-0.16

Point

-0.16

eydi

-0.16

éĢģæĸĻçĦ¡æĸĻ

-0.15

iership

-0.15

.ManyToMany

-0.15

cycle

-0.15

 MEDIATEK

-0.15

POSITIVE LOGITS

Om

0.20

omb

0.20

om

0.19

av

0.19

ats

0.17

ol

0.17

am

0.17

Il

0.17

om

0.17

Om

0.17

Activations Density 0.048%

phrases related to software licensing and terms of use

No Comments

No Known Activations