INDEX

Explanations

references to various types of visual media and their attributes

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

Ð²ÐµÐ´Ð¸ÑĤÐµ

-0.28

ÑģÐµ

-0.26

-0.23

EK

-0.23

-0.22

ar

-0.22

MUX

-0.21

POSITIVE LOGITS

ehicles

0.21

ariance

0.19

AILABLE

0.19

enus

0.18

ARIABLE

0.18

eer

0.18

ancouver

0.18

illage

0.18

egas

0.17

iolet

0.17

Activations Density 0.033%

references to various types of visual media and their attributes

No Comments

No Known Activations