INDEX

Explanations

questions or references to the concept of "why."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

al

-0.17

aint

-0.15

mode

-0.15

ahas

-0.14

STYPE

-0.14

oogle

-0.14

ÙĬÙĨÙĬ

-0.14

tran

-0.13

ize

-0.13

amo

-0.13

POSITIVE LOGITS

why

0.23

why

0.20

itzer

0.20

soever

0.19

/how

0.18

ê³¡

0.17

WHY

0.16

vertising

0.15

Why

0.14

ema

0.14

Activations Density 0.040%

questions or references to the concept of "why."

No Comments

No Known Activations