INDEX

Explanations

references to the letter "M" or phrases where it appears frequently, likely indicating the presence of names or titles starting with that letter

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

pell

-0.17

atform

-0.15

-Requested

-0.15

oppel

-0.15

elow

-0.15

anship

-0.15

YGON

-0.14

strand

-0.14

.Unity

-0.14

velle

-0.14

POSITIVE LOGITS

orsi

0.31

ide

0.30

ullah

0.29

ub

0.29

ilit

0.28

uslim

0.28

uft

0.26

igrants

0.25

igrant

0.25

ubar

0.25

Activations Density 0.027%

references to the letter "M" or phrases where it appears frequently, likely indicating the presence of names or titles starting with that letter

No Comments

No Known Activations