INDEX

Explanations

references to Mr. or Mrs. within the context of conversations

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

fern

-0.16

ep

-0.16

ëį°

-0.15

coholic

-0.15

rien

-0.15

azÄĥ

-0.15

usu

-0.14

endas

-0.14

ons

-0.14

ledge

-0.14

POSITIVE LOGITS

zek

0.15

à¸¥à¸°

0.15

ified

0.14

ê

0.14

kus

0.14

Ð¸Ð½Ðµ

0.14

kara

0.14

ships

0.14

.joda

0.14

wahl

0.14

Activations Density 0.129%

references to Mr. or Mrs. within the context of conversations

No Comments

No Known Activations