INDEX

Explanations

references to health-related factors and their impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

elize

-0.15

esModule

-0.15

);;↵

-0.14

ancock

-0.14

isti

-0.14

atform

-0.13

agram

-0.13

zioni

-0.13

istani

-0.13

POSITIVE LOGITS

 plays

0.51

 play

0.50

 factor

0.45

 played

0.45

 contrib

0.44

 contribute

0.41

play

0.41

contrib

0.41

 contributes

0.41

 factors

0.40

Activations Density 0.136%

references to health-related factors and their impacts

No Comments

No Known Activations