INDEX

Explanations

evaluative language expressing recommendations or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-Fi

-0.15

abilmek

-0.14

ilda

-0.14

Ð»ÑıÑħ

-0.14

-0.13

_Current

-0.13

ibal

-0.13

engu

-0.13

 Brilliant

-0.13

umping

-0.13

POSITIVE LOGITS

 worth

1.01

 Worth

0.84

worth

0.77

 worthy

0.63

 deserves

0.58

 deserve

0.57

worthy

0.55

 deserving

0.49

 warrant

0.48

 merits

0.48

Activations Density 0.348%

evaluative language expressing recommendations or opinions

No Comments

No Known Activations