INDEX

Explanations

phrases that indicate presence or status in relation to personal or legal interactions

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

Ïĥ

-0.16

endor

-0.14

vat

-0.14

undy

-0.14

eln

-0.14

ols

-0.14

ppo

-0.14

oui

-0.14

oul

-0.14

ilig

-0.14

POSITIVE LOGITS

 Kostenlose

0.14

reas

0.14

 Marketable

0.14

Wunused

0.13

irmware

0.13

yte

0.13

Ð°ÑĤÑĥ

0.13

 Beste

0.13

Ð¸ÑĤÐ¸

0.13

Activations Density 0.093%

phrases that indicate presence or status in relation to personal or legal interactions

No Comments

No Known Activations