INDEX

Explanations

emotional expressions and sentiments related to well-being and sadness

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

ÅĤÄħ

-0.16

 addCriterion

-0.16

-fontawesome

-0.16

 turno

-0.15

ledo

-0.14

cona

-0.14

.toolbox

-0.14

ampaign

-0.14

.hist

-0.14

erdale

-0.14

POSITIVE LOGITS

 Meghan

0.35

Meg

0.32

 Sussex

0.32

 Harry

0.32

 royal

0.31

Harry

0.28

 Archie

0.28

 Royal

0.27

 Prince

0.27

 Frog

0.26

Activations Density 0.024%

emotional expressions and sentiments related to well-being and sadness

No Comments

No Known Activations