INDEX

Explanations

mentions of Disney and its related properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

venes

-0.17

sed

-0.16

akra

-0.15

OfMonth

-0.15

sWith

-0.14

ÑĢÑĸÑı

-0.14

opsis

-0.14

istributor

-0.14

akis

-0.14

Ĺi

-0.14

POSITIVE LOGITS

 Parks

0.27

land

0.24

 Channel

0.23

Bounding

0.23

 Cruise

0.23

 Springs

0.22

LAND

0.21

bounding

0.20

world

0.20

 parks

0.20

Activations Density 0.005%

mentions of Disney and its related properties

No Comments

No Known Activations