INDEX

Explanations

terms related to dignity, respect, and the undermining of these concepts in social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ÙħÙĦ

-0.15

åĬ

-0.14

æľĹ

-0.14

BAB

-0.13

orrh

-0.13

ÙĤÙħ

-0.13

ãĤ±ãĥĥãĥĪ

-0.13

manifest

-0.13

kek

-0.13

POSITIVE LOGITS

 dignity

0.47

 dign

0.36

 honor

0.31

 pride

0.31

 honour

0.29

 integrity

0.28

 insult

0.25

å°Ĭ

0.25

 reputation

0.24

 Pride

0.24

Activations Density 0.095%

terms related to dignity, respect, and the undermining of these concepts in social interactions

No Comments

No Known Activations