INDEX

Explanations

phrases that indicate significant changes or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

riot

-0.15

åĹ

-0.14

entai

-0.14

 Replies

-0.14

ners

-0.14

ssid

-0.14

.scalablytyped

-0.14

Ð¾Ð»ÑĮÐ½Ð¾

-0.13

oui

-0.13

zz

-0.13

POSITIVE LOGITS

fi

0.16

0.15

çī

0.15

 Belt

0.15

ł

0.14

 Liver

0.14

addir

0.14

/rfc

0.13

nom

0.13

tak

0.13

Activations Density 0.079%

phrases that indicate significant changes or trends

No Comments

No Known Activations