INDEX

Explanations

various book or media series and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ov

-0.14

ruit

-0.14

/cards

-0.14

Cors

-0.14

 Herz

-0.14

Ã©ri

-0.13

aub

-0.13

icut

-0.13

POSITIVE LOGITS

.userInteractionEnabled

0.17

 Burr

0.16

isd

0.15

Fa

0.14

iram

0.14

Moo

0.14

lington

0.14

à¥įà¤¦

0.13

ementia

0.13

aisy

0.13

Activations Density 0.361%

various book or media series and their components

No Comments

No Known Activations