INDEX

Explanations

incidents involving gun violence

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

uras

-0.17

 Knife

-0.17

 Sword

-0.15

è´¨

-0.15

Knife

-0.15

FLT

-0.15

 à¤Ķ

-0.15

 swords

-0.15

-0.14

 Bomb

-0.14

POSITIVE LOGITS

 shots

0.29

shots

0.26

 shot

0.26

 shooting

0.24

 shoot

0.24

 bullet

0.23

 firing

0.23

 fired

0.23

bullet

0.21

 bullets

0.21

Activations Density 0.098%

incidents involving gun violence

No Comments

No Known Activations