INDEX

Explanations

instances of passive voice and mentions of people in vulnerable situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 ÙħÙĨØª

-0.15

engkap

-0.15

 cripp

-0.15

WXYZ

-0.15

Ã¡ce

-0.15

venture

-0.14

usters

-0.14

éŁ¿

-0.14

odesk

-0.14

JsonValue

-0.14

POSITIVE LOGITS

 hass

0.25

 targeted

0.24

 lect

0.24

amb

0.24

 attacked

0.23

 barr

0.22

 corner

0.22

 stalk

0.22

 bomb

0.22

 chew

0.21

Activations Density 0.210%

instances of passive voice and mentions of people in vulnerable situations

No Comments

No Known Activations