INDEX

Explanations

references to educational programs and student grades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ã¼gen

-0.16

ivr

-0.15

aise

-0.15

 Fortress

-0.15

misc

-0.15

iversit

-0.14

UNT

-0.14

 Ð¿Ð¾Ð»Ñı

-0.14

azy

-0.14

erno

-0.14

POSITIVE LOGITS

 grade

0.46

 Grade

0.37

 grades

0.35

grade

0.32

-grade

0.32

Grade

0.31

 ninth

0.29

.grade

0.28

 eighth

0.28

 seventh

0.27

Activations Density 0.250%

references to educational programs and student grades

No Comments

No Known Activations