INDEX

Explanations

references to interactions and connections among individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

DF

-0.17

arro

-0.15

upro

-0.15

acter

-0.14

iore

-0.14

 downward

-0.14

gor

-0.14

df

-0.14

çĦ

-0.14

foot

-0.14

POSITIVE LOGITS

 hostage

0.26

 places

0.23

 seriously

0.22

 away

0.18

Places

0.17

 Places

0.17

 apart

0.17

eya

0.17

_places

0.16

 Seriously

0.16

Activations Density 0.033%

references to interactions and connections among individuals and organizations

No Comments

No Known Activations