INDEX

Explanations

concepts related to domestic violence and mental health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

nez

-0.17

gio

-0.16

dÄĽ

-0.14

vrier

-0.14

ursed

-0.14

utron

-0.14

nable

-0.14

deaux

-0.14

uren

-0.14

.getTag

-0.13

POSITIVE LOGITS

 domestic

0.52

 Domestic

0.49

 batter

0.42

 Batter

0.38

 violence

0.37

 domest

0.37

Dom

0.35

 abuse

0.35

/dom

0.34

 battered

0.34

Activations Density 0.095%

concepts related to domestic violence and mental health

No Comments

No Known Activations