INDEX

Explanations

occurrences of HTML class attributes in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oven

-0.15

alesce

-0.14

 chá»ĭu

-0.14

Unnamed

-0.13

ãĥ³ãĥĨ

-0.13

iversal

-0.13

ximity

-0.13

.nr

-0.13

aviest

-0.13

ead

-0.13

POSITIVE LOGITS

//**↵

0.15

 Surge

0.14

âĺħâĺħ

0.14

amping

0.14

hab

0.14

 Barnett

0.13

ucci

0.13

nech

0.13

ForMember

0.13

 Olsen

0.13

Activations Density 0.015%

occurrences of HTML class attributes in the document

No Comments

No Known Activations