INDEX

Explanations

references to scheduled events or meetings

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

ienen

-0.15

luc

-0.14

enor

-0.14

aÃ§Ã£o

-0.14

lo

-0.14

cl

-0.14

 âĹĦ

-0.13

amma

-0.13

inn

-0.13

Gun

-0.13

POSITIVE LOGITS

à¸Ľà¸£à¸°à¸Īà¸³

0.15

NavController

0.15

arton

0.15

ãģ¬

0.15

ë§Īëĭ¤

0.15

0.14

.ElementAt

0.14

OrCreate

0.14

ONTAL

0.14

Activations Density 0.101%

references to scheduled events or meetings

No Comments

No Known Activations