INDEX

Explanations

terms related to educational programs and learning environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

enna

-0.18

abilia

-0.14

/Area

-0.14

 undergraduate

-0.14

 Ferguson

-0.14

uddy

-0.14

ntag

-0.13

rych

-0.13

zew

-0.13

Cav

-0.13

POSITIVE LOGITS

_BOARD

0.17

ospace

0.17

boys

0.16

 ÑĢÑĥÐ±

0.16

 girls

0.15

 boys

0.15

 boarding

0.15

avi

0.14

girls

0.14

 Geld

0.14

Activations Density 0.001%

terms related to educational programs and learning environments

No Comments

No Known Activations