INDEX

Explanations

the word "big" and variations of its usage, indicating a focus on significance or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

urence

-0.16

prus

-0.15

Ú¯Ø§Ùĩ

-0.15

ncia

-0.14

ope

-0.14

ollower

-0.14

oden

-0.14

itage

-0.14

ponce

-0.14

Ð´Ð°Ð¼

-0.13

POSITIVE LOGITS

oted

0.22

gie

0.16

wig

0.16

elow

0.16

elters

0.16

 tuá»ķi

0.16

ween

0.15

ging

0.15

-ticket

0.15

-picture

0.15

Activations Density 0.039%

the word "big" and variations of its usage, indicating a focus on significance or intensity

No Comments

No Known Activations