INDEX

Explanations

brand names or specific product references related to gaming and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

tainment

-0.15

à¸Ĳà¸²à¸Ļ

-0.15

azer

-0.14

Nej

-0.14

kowski

-0.14

ouro

-0.14

awl

-0.14

ices

-0.14

 McGr

-0.13

éĻ¢

-0.13

POSITIVE LOGITS

sonian

0.17

ruk

0.16

ÏĦÎ¹Îº

0.15

Yo

0.15

åİħ

0.15

nor

0.15

uls

0.15

cert

0.15

0.14

chod

0.14

Activations Density 0.073%

brand names or specific product references related to gaming and technology

No Comments

No Known Activations