INDEX

Explanations

words or symbols that indicate complex mathematical or scientific theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÄĻd

-0.17

ucht

-0.15

ÙĬÙĦØ§

-0.14

pmat

-0.14

oppins

-0.14

.pack

-0.14

_strerror

-0.14

ondo

-0.14

 Interr

-0.13

ebnÃŃ

-0.13

POSITIVE LOGITS

bos

0.28

 production

0.26

SM

0.25

 decay

0.25

 searches

0.25

dib

0.24

 signal

0.24

CMS

0.24

dip

0.23

iggs

0.23

Activations Density 0.007%

words or symbols that indicate complex mathematical or scientific theories

No Comments

No Known Activations

words or symbols that indicate complex mathematical or scientific theories

No Comments

No Known Activations