INDEX

Explanations

information related to educational and professional backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

awan

-0.15

 apellido

-0.14

iÄįka

-0.13

.jdesktop

-0.13

ulia

-0.13

oyer

-0.13

hiba

-0.13

 Hass

-0.13

ÏĦÎ¿Î¼Î±

-0.13

 Heller

-0.12

POSITIVE LOGITS

_N

0.42

_n

0.36

ÂłN

0.34

 à¤¨

0.33

.N

0.33

Âłn

0.32

.n

0.32

0.31

 ÐĿ

0.31

 ÙĨ

0.31

Activations Density 0.613%

information related to educational and professional backgrounds

No Comments

No Known Activations