INDEX

Explanations

terms related to death and mortality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

assen

-0.16

ocale

-0.15

OrElse

-0.15

osaic

-0.15

warts

-0.15

alars

-0.15

oha

-0.15

ProgressHUD

-0.15

acific

-0.14

ripp

-0.14

POSITIVE LOGITS

 anonymous

0.15

UTTON

0.15

 Blow

0.15

utton

0.15

 prez

0.15

 blows

0.15

zon

0.15

oze

0.15

_ENGINE

0.14

ilon

0.14

Activations Density 0.187%

terms related to death and mortality

No Comments

No Known Activations