INDEX

Explanations

instances of questioning or inquiry 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

oola

-0.16

anÃ¡

-0.15

(problem

-0.15

_instr

-0.15

à¸ŀà¸¥

-0.14

otti

-0.14

leck

-0.14

_problem

-0.14

ÙĪØ±Ø©

-0.14

.scalablytyped

-0.14

POSITIVE LOGITS

 questions

0.37

 burning

0.32

 tough

0.31

questions

0.28

 Questions

0.27

Questions

0.25

 Burning

0.23

.questions

0.23

 penetrating

0.23

 QUEST

0.22

Activations Density 0.081%

instances of questioning or inquiry in the text

No Comments

No Known Activations