INDEX

Explanations

references to sonic elements and auditory experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

éĸ

-0.17

 Duffy

-0.16

 Observer

-0.15

tre

-0.15

 referrals

-0.15

Zwe

-0.14

 Clair

-0.14

UA

-0.14

 preg

-0.14

POSITIVE LOGITS

optera

0.16

utex

0.16

.Keyword

0.15

ãģ£ãģı

0.15

ÐµÑİ

0.15

çĳŁ

0.15

%B

0.15

onica

0.15

_twitter

0.15

"<?

0.15

Activations Density 0.008%

references to sonic elements and auditory experiences

No Comments

No Known Activations