INDEX

Explanations

references to specific universities, particularly those in California

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ize

-0.16

 Wolverine

-0.14

ane

-0.14

Ð¸Ð½Ð¾Ðº

-0.14

Esk

-0.13

ixe

-0.13

oi

-0.13

aska

-0.13

 classic

-0.13

.uf

-0.13

POSITIVE LOGITS

 Hayward

0.26

 Doming

0.23

 Stan

0.22

 Long

0.21

 Channel

0.20

 Full

0.20

 North

0.19

Pom

0.18

-dom

0.18

(Long

0.18

Activations Density 0.003%

references to specific universities, particularly those in California

No Comments

No Known Activations