INDEX

Explanations

references to historical or significant events, figures, and their impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

InView

-0.19

ONTAL

-0.18

.scalablytyped

-0.15

ÙĬÙĨØ§

-0.15

Ã¢u

-0.14

umer

-0.14

sez

-0.14

èĭĹ

-0.14

abox

-0.14

rome

-0.14

POSITIVE LOGITS

 origin

0.35

 fame

0.32

 nature

0.32

 importance

0.30

 magnitude

0.30

 significance

0.29

 Importance

0.27

 proportions

0.26

ilk

0.25

 renown

0.24

Activations Density 0.137%

references to historical or significant events, figures, and their impact

No Comments

No Known Activations