INDEX

Explanations

the word "just" and its variants in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

èĩ³å°ĳ

-0.17

ÙħÛĮÙĦ

-0.16

 atleast

-0.16

 UsersController

-0.15

MING

-0.13

 ëª¨ëĳĲ

-0.13

others

-0.13

 ç«

-0.12

 elsewhere

-0.12

WARDED

-0.12

POSITIVE LOGITS

 minimal

0.24

 minor

0.24

 token

0.23

 trace

0.23

one

0.23

rud

0.22

 modest

0.22

 basic

0.22

 single

0.21

 moderate

0.21

Activations Density 0.066%

the word "just" and its variants in various contexts

No Comments

No Known Activations