INDEX

Explanations

references to casualties and injuries in violent incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

krom

-0.15

 murderer

-0.15

Sink

-0.15

ÙĨØ§ÙħÙĩ

-0.15

 AÅŁ

-0.14

uet

-0.14

 murderers

-0.14

acom

-0.14

zug

-0.14

thag

-0.14

POSITIVE LOGITS

 injured

0.56

 wounded

0.52

 injury

0.51

 injuries

0.50

 Injury

0.45

 seriously

0.43

 injuring

0.39

inj

0.37

 wounds

0.36

ä¼¤

0.36

Activations Density 0.163%

references to casualties and injuries in violent incidents

No Comments

No Known Activations