INDEX

Explanations

references to the social media platform Twitter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oo

-0.16

opak

-0.15

overe

-0.15

lov

-0.15

ost

-0.15

 pragma

-0.14

olly

-0.14

Boh

-0.14

 Ning

-0.14

.bukkit

-0.13

POSITIVE LOGITS

ÚĨÛĮ

0.16

/twitter

0.15

ati

0.15

0.14

 ********************************************************************************

0.14

walking

0.14

Ä±rak

0.14

çī

0.14

izzo

0.14

ath

0.14

Activations Density 0.019%

references to the social media platform Twitter

No Comments

No Known Activations