INDEX

Explanations

references to domestic violence and related support services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

gio

-0.18

roit

-0.16

haft

-0.15

Ð°ÑĢÐ¾Ð´

-0.15

adt

-0.14

à¤¾à¤§

-0.14

ospital

-0.13

æ²¿

-0.13

umlu

-0.13

nable

-0.13

POSITIVE LOGITS

 domestic

0.51

 Domestic

0.49

 batter

0.43

 Batter

0.38

 domest

0.38

Dom

0.35

 abuse

0.34

 violence

0.34

/dom

0.34

 battery

0.33

Activations Density 0.093%

references to domestic violence and related support services

No Comments

No Known Activations