INDEX

Explanations

information related to specific locations and business operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

strup

-0.16

.synthetic

-0.16

beits

-0.15

 actionTypes

-0.15

oten

-0.15

ETS

-0.14

bjerg

-0.14

isku

-0.14

 Hunts

-0.14

alue

-0.14

POSITIVE LOGITS

 Melbourne

0.34

 Victoria

0.23

 Victorian

0.22

 Caul

0.21

Victoria

0.19

 Batman

0.19

VIC

0.18

Mel

0.17

 Bend

0.17

 Michigan

0.17

Activations Density 0.081%

information related to specific locations and business operations

No Comments

No Known Activations