INDEX

Explanations

references to pandemics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Refriger

-0.14

ÑĢÑĥÐ¶

-0.14

lop

-0.14

SSL

-0.14

eed

-0.14

Ð´ÐµÐ»

-0.13

/apt

-0.13

 Distance

-0.13

iced

-0.13

ÑĤÐ°Ñħ

-0.13

POSITIVE LOGITS

 Curry

0.16

.CV

0.16

ofile

0.15

 Curse

0.14

 Hayward

0.14

 Ø´ÙĥÙĦ

0.14

olson

0.14

chu

0.14

 curse

0.14

pics

0.14

Activations Density 0.003%

references to pandemics

No Comments

No Known Activations