INDEX

Explanations

information related to academic performance and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

erset

-0.17

iska

-0.15

@dynamic

-0.15

ASC

-0.15

-0.14

ASY

-0.14

enta

-0.14

sty

-0.14

 training

-0.14

imer

-0.14

POSITIVE LOGITS

GPA

0.22

 grades

0.22

 academic

0.20

 Dean

0.20

sch

0.19

Dean

0.19

 scores

0.19

 marks

0.19

 score

0.18

ç»©

0.18

Activations Density 0.146%

information related to academic performance and qualifications

No Comments

No Known Activations