INDEX

Explanations

references to new content and announcements in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

icio

-0.16

artin

-0.14

ony

-0.14

ogy

-0.14

artz

-0.14

nelly

-0.14

URLRequest

-0.13

eparator

-0.13

fore

-0.13

AZY

-0.13

POSITIVE LOGITS

ãĥ¥ãĥ¼

0.15

reve

0.14

 Kosten

0.14

GPC

0.14

bos

0.14

 Aggregate

0.14

alist

0.14

EventData

0.14

åħ¬å¼Ģ

0.13

Activations Density 0.031%

references to new content and announcements in media

No Comments

No Known Activations