INDEX

Explanations

terms related to risk assessment and public health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Abrams

-0.17

reet

-0.16

atron

-0.16

edo

-0.15

ÐµÐ²Ð¸

-0.14

usher

-0.14

 Prelude

-0.14

ODO

-0.14

æĭĶ

-0.14

ì§ĵ

-0.14

POSITIVE LOGITS

 toxicity

0.24

 chemicals

0.24

 Toxic

0.22

 OECD

0.22

 toxic

0.21

 hazard

0.21

xic

0.21

 endpoints

0.20

 fate

0.20

 pesticide

0.19

Activations Density 0.046%

terms related to risk assessment and public health

No Comments

No Known Activations