INDEX

Explanations

data and references related to statistics or numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ano

-0.17

æķ·

-0.17

OrElse

-0.14

omers

-0.14

ileo

-0.14

avg

-0.13

ÙĨÙħ

-0.13

endar

-0.13

NM

-0.13

nard

-0.13

POSITIVE LOGITS

éŁ¿

0.17

yon

0.14

tro

0.14

à¸ĭ

0.13

 convers

0.13

RAL

0.13

arkin

0.13

hod

0.13

ynÄ±

0.13

amber

0.13

Activations Density 0.012%

data and references related to statistics or numbers

No Comments

No Known Activations