INDEX

Explanations

instances of the word "multiple" and variations of it, indicating a focus on various quantities, options, or instances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ses

-0.16

sembl

-0.16

editary

-0.15

yonel

-0.15

ruptcy

-0.15

bone

-0.15

bound

-0.15

itable

-0.14

bo

-0.14

ibo

-0.14

POSITIVE LOGITS

 sclerosis

0.28

-purpose

0.16

aney

0.15

arb

0.15

licity

0.15

asking

0.15

erc

0.14

.sourceforge

0.14

/int

0.14

acro

0.14

Activations Density 0.045%

instances of the word "multiple" and variations of it, indicating a focus on various quantities, options, or instances

No Comments

No Known Activations