INDEX

Explanations

occurrences of the word "I" and its variations to identify personal statements or opinions

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

spark

-0.23

/Sub

-0.22

STEM

-0.21

/spec

-0.21

slider

-0.21

Scanner

-0.21

spinner

-0.20

 Salisbury

-0.20

Spark

-0.20

 Salvador

-0.20

POSITIVE LOGITS

0.29

0.27

_S

0.27

Âłs

0.27

 à¤¸

0.26

ÂłS

0.25

 ãĤ¹

0.23

-S

0.23

 Ø³

0.23

Activations Density 0.110%

occurrences of the word "I" and its variations to identify personal statements or opinions

No Comments

No Known Activations