INDEX

Explanations

titles of works and references to actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.15

ÑĥÑģÐ°

-0.15

 slik

-0.15

.weixin

-0.14

ollah

-0.14

 nackte

-0.14

Ð²Ð°Ð¹

-0.14

 uncomment

-0.14

 Sanat

-0.13

POSITIVE LOGITS

 BaseService

0.15

 Diamond

0.14

 Ruiz

0.14

éĩİ

0.14

 tend

0.14

 subsidi

0.14

dio

0.13

imore

0.13

Rav

0.13

xB

0.13

Activations Density 0.206%

titles of works and references to actions or events

No Comments

No Known Activations