INDEX

Explanations

phrases indicating periods of time or experiences in a person's life

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 atleast

-0.16

latable

-0.15

imed

-0.14

 alespoÅĪ

-0.14

 Beit

-0.14

_IRQHandler

-0.14

Ú¯ÙĪ

-0.14

áº©m

-0.14

Ø§Ø¯Ùĩ

-0.14

POSITIVE LOGITS

 years

0.23

 briefly

0.23

 Jahre

0.19

 Years

0.18

 almost

0.18

two

0.17

 brief

0.17

 three

0.17

 several

0.17

 nearly

0.17

Activations Density 0.103%

phrases indicating periods of time or experiences in a person's life

No Comments

No Known Activations