INDEX

Explanations

variations of the word "Calabasas" and related terms associated with it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.15

actable

-0.14

 fired

-0.14

mlin

-0.14

ÑĥÑĤÐ¸

-0.14

Dak

-0.14

labels

-0.14

ksam

-0.13

ething

-0.13

ijke

-0.13

POSITIVE LOGITS

(cal

0.20

/cal

0.18

eyn

0.18

Cal

0.17

OUN

0.16

Cal

0.16

 Cald

0.15

urge

0.15

aign

0.15

oun

0.15

Activations Density 0.023%

variations of the word "Calabasas" and related terms associated with it

No Comments

No Known Activations