INDEX

Explanations

vulnerabilities in various contexts, such as environmental, health, and social factors

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

POCH

-0.16

phia

-0.15

UA

-0.15

ostel

-0.14

 Superior

-0.14

BOSE

-0.14

ÏĦÏĥ

-0.14

zel

-0.14

ippi

-0.13

POSITIVE LOGITS

 vulnerable

0.50

 susceptible

0.42

 vulnerability

0.41

 Vulner

0.39

 suscept

0.39

0.37

 exposed

0.36

ulnerable

0.36

 vulner

0.35

Âłv

0.35

Activations Density 0.125%

vulnerabilities in various contexts, such as environmental, health, and social factors

No Comments

No Known Activations