INDEX

Explanations

phrases related to personal relationships and emotional dependencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 themselves

-0.42

 itself

-0.35

 kita

-0.17

ald

-0.16

 Ø®ÙĪØ¯Ø´

-0.16

ÄĽl

-0.15

esin

-0.15

alm

-0.15

 himself

-0.15

os

-0.15

POSITIVE LOGITS

 yourself

0.82

 Yourself

0.55

 yourselves

0.54

 your

0.46

your

0.43

ä½łçļĦ

0.39

Your

0.30

 Ð²Ð°ÑĪ

0.29

 Ð¼Ð¾Ð¶ÐµÑĤÐµ

0.28

 votre

0.27

Activations Density 1.150%

phrases related to personal relationships and emotional dependencies

No Comments

No Known Activations