INDEX

Explanations

phrases indicating collective experiences or situations involving multiple people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ç»ĻæĪĳ

-0.24

 themselves

-0.23

 itself

-0.22

us

-0.21

è®©æĪĳ

-0.20

 himself

-0.19

us

-0.17

 herself

-0.16

me

-0.16

mij

-0.15

POSITIVE LOGITS

 ourselves

0.81

ÑħÐ¾Ð´Ð¸Ð¼

0.36

ours

0.34

our

0.32

 abych

0.32

 Ð¼Ð¾Ð¶

0.27

 Ð½Ð°ÑĪÐ¸Ñħ

0.26

ï¼ĮæĪĳä»¬

0.26

 jsme

0.26

 selves

0.26

Activations Density 2.138%

phrases indicating collective experiences or situations involving multiple people

No Comments

No Known Activations