INDEX

Explanations

phrases related to education and learning, emphasizing different aspects of the learning process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

yla

-0.15

acas

-0.14

ì§Ģëħ¸

-0.14

&type

-0.14

-urlencoded

-0.14

adelphia

-0.14

ÑĥÐ²

-0.13

ÑĮÐºÐ¾

-0.13

 Simpson

-0.13

 suspects

-0.13

POSITIVE LOGITS

GRES

0.15

adem

0.15

wich

0.15

ertz

0.15

 segment

0.14

 visual

0.14

ersh

0.14

wort

0.14

duct

0.13

.rm

0.13

Activations Density 0.304%

phrases related to education and learning, emphasizing different aspects of the learning process

No Comments

No Known Activations