INDEX

Explanations

educational programs and degrees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 IOCTL

-0.17

èŀº

-0.16

anza

-0.15

ISCO

-0.14

_NC

-0.14

agal

-0.14

ÏĩÎ±Î½

-0.14

_vue

-0.14

okie

-0.14

ìĮ

-0.13

POSITIVE LOGITS

 Oxford

0.40

 Cambridge

0.24

xford

0.22

 Harvard

0.19

curacy

0.17

 Princeton

0.17

 Yale

0.17

iox

0.15

 pang

0.15

 Thames

0.15

Activations Density 0.100%

educational programs and degrees

No Comments

No Known Activations