INDEX

Explanations

the repetitive use of the word "just" 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 prÃ¡vÄĽ

-0.16

enden

-0.16

oot

-0.15

rup

-0.15

rates

-0.15

iesel

-0.15

 iÅŁte

-0.14

 Ð¸Ð¼ÐµÐ½Ð½Ð¾

-0.14

rating

-0.14

 thus

-0.14

POSITIVE LOGITS

ifiable

0.43

ifi

0.41

ifying

0.38

ifies

0.36

ifications

0.35

ified

0.29

ification

0.26

IFI

0.25

 plain

0.23

ifiers

0.22

Activations Density 0.100%

the repetitive use of the word "just" in various contexts

No Comments

No Known Activations