INDEX

Explanations

phrases related to emotional responses and interpersonal relationships

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

à¹Ģà¸Ńà¸ĩ

-0.17

amins

-0.17

 sebou

-0.17

entials

-0.17

him

-0.16

 Humans

-0.15

 mÃ¬nh

-0.15

éº

-0.14

à¸Ńà¸ļ

-0.14

gregar

-0.14

POSITIVE LOGITS

 their

0.43

 THEIR

0.36

 peoples

0.33

their

0.32

 everyone

0.31

 Their

0.31

Their

0.30

 deren

0.30

 theirs

0.30

 everybody

0.29

Activations Density 0.547%

phrases related to emotional responses and interpersonal relationships

No Comments

No Known Activations