INDEX

Explanations

references to education and teaching activities

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

istle

-0.15

à¤Ł

-0.15

ibling

-0.14

rowsable

-0.14

erras

-0.14

ULO

-0.14

Øº

-0.14

ANTLR

-0.14

phin

-0.14

 Sanford

-0.14

POSITIVE LOGITS

 classes

0.21

 several

0.19

 topics

0.18

at

0.18

 courses

0.17

 classe

0.17

 workshops

0.17

 teaches

0.17

classes

0.16

 teach

0.16

Activations Density 0.095%

references to education and teaching activities

No Comments

No Known Activations