INDEX

Explanations

references to licensing or licensure status

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

han

-0.16

istributor

-0.15

ki

-0.14

akis

-0.14

WP

-0.14

rig

-0.14

ãĥ¼ãĥģ

-0.14

Mou

-0.14

pu

-0.13

Ļ¨

-0.13

POSITIVE LOGITS

RLF

0.18

ÑĥÐµÑĤ

0.16

_HT

0.16

elon

0.15

emade

0.15

 goose

0.15

ione

0.14

à¸±à¸ģà¸ģ

0.14

UTO

0.14

Activations Density 0.003%

references to licensing or licensure status

No Comments

No Known Activations