INDEX

Explanations

terms and phrases related to actions and contexts involving "as" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

oire

-0.16

oki

-0.15

ANJI

-0.15

Ã¡Å¡

-0.15

ÙĪØ±Ø´

-0.14

imo

-0.13

à¸ªà¸¥

-0.13

meld

-0.13

arten

-0.13

obao

-0.13

POSITIVE LOGITS

 part

0.49

 ÑĩÐ°ÑģÑĤÑĮ

0.30

 parte

0.28

_part

0.27

 Part

0.27

way

0.27

 Ø¨Ø®Ø´ÛĮ

0.26

part

0.25

 PART

0.24

.part

0.24

Activations Density 0.099%

terms and phrases related to actions and contexts involving "as" and its variants

No Comments

No Known Activations