INDEX

Explanations

references to legal or professional services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ithe

-0.17

uyla

-0.17

czy

-0.16

uper

-0.15

ialized

-0.15

itial

-0.15

ynamo

-0.15

 Colbert

-0.14

Hut

-0.14

uC

-0.14

POSITIVE LOGITS

ghi

0.20

Dan

0.18

NSNotification

0.15

FUNC

0.15

Dan

0.15

 Bonds

0.14

 suspend

0.14

lab

0.14

RectTransform

0.14

IDO

0.14

Activations Density 0.014%

references to legal or professional services

No Comments

No Known Activations