INDEX

Explanations

references to law enforcement and legal obligations related to alcohol consumption

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

Thy

-0.16

oled

-0.15

itters

-0.15

.AutoComplete

-0.15

deg

-0.14

aran

-0.14

 ç·

-0.14

é¡

-0.14

erval

-0.14

ĴĮ

-0.14

POSITIVE LOGITS

éħĴ

0.23

 alcohol

0.23

 breath

0.22

 drunk

0.22

sob

0.22

 drunken

0.21

sob

0.21

éĨ

0.20

 Breath

0.20

DUI

0.19

Activations Density 0.009%

references to law enforcement and legal obligations related to alcohol consumption

No Comments

No Known Activations