INDEX

Explanations

references to product release dates and related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

zioni

-0.14

åº§

-0.14

 recent

-0.13

 Recent

-0.13

 Gast

-0.13

incinn

-0.13

 fair

-0.13

orce

-0.13

 Bourbon

-0.12

POSITIVE LOGITS

ìĮ

0.16

addtogroup

0.16

odash

0.15

SystemService

0.15

_DECLARE

0.14

oret

0.14

 è©ķä¾¡

0.14

¬Ĥ

0.13

ycastle

0.13

eldorf

0.13

Activations Density 0.202%

references to product release dates and related events

No Comments

No Known Activations