INDEX

Explanations

commas in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

-0.17

lace

-0.15

hip

-0.15

fact

-0.14

iaz

-0.14

¨

-0.14

hist

-0.14

å¤ķ

-0.14

oir

-0.14

 Lace

-0.13

POSITIVE LOGITS

upp

0.16

 pÃ¡s

0.15

ancel

0.15

Marshal

0.14

-dismiss

0.14

SelfPermission

0.14

Ð°Ð½ÑģÐ¸

0.14

velt

0.14

bane

0.14

inÃ§

0.14

Activations Density 0.009%

commas in the text

No Comments

No Known Activations