INDEX

Explanations

terms related to fandom or enthusiasts of a particular subject or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

chia

-0.17

izador

-0.16

iating

-0.16

guards

-0.16

naires

-0.15

ides

-0.15

ikal

-0.15

åĿĬ

-0.15

bjerg

-0.15

aign

-0.15

POSITIVE LOGITS

atical

0.32

fare

0.30

atics

0.28

atic

0.24

etic

0.21

atically

0.21

ancial

0.19

ERGY

0.17

club

0.17

atik

0.17

Activations Density 0.010%

terms related to fandom or enthusiasts of a particular subject or entity

No Comments

No Known Activations