INDEX

Explanations

terms related to regulations and guidelines

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

InputDialog

-0.19

AFE

-0.17

WidgetItem

-0.17

antino

-0.15

voor

-0.15

eldo

-0.15

ardy

-0.14

ãĥ¼ãĥľ

-0.14

voie

-0.14

avana

-0.14

POSITIVE LOGITS

shift

0.17

paren

0.17

 Erect

0.17

umi

0.15

pert

0.14

">//

0.14

arr

0.14

 shift

0.14

Activations Density 0.200%

terms related to regulations and guidelines

No Comments

No Known Activations